Robust Spike-Based Continual Meta-Learning Improved by Restricted Minimum Error Entropy Criterion

Bio-inspired computational memory model of the Hippocampus: An approach to a neuromorphic spike-based Content-Addressable Memory

The brain has computational capabilities that surpass those of modern systems, being able to solve complex problems efficiently in a simple way. Neuromorphic engineering aims to mimic biology in order to develop new systems capable of incorporating such capabilities. Bio-inspired learning systems continue to be a challenge that must be solved, and much work needs to be done in this regard. Among all brain regions, the hippocampus stands out as an autoassociative short-term memory with the capacity to learn and recall memories from any fragment of them. These characteristics make the hippocampus an ideal candidate for developing bio-inspired learning systems that, in addition, resemble content-addressable memories. Therefore, in this work we propose a bio-inspired spiking content-addressable memory model based on the CA3 region of the hippocampus with the ability to learn, forget and recall memories, both orthogonal and non-orthogonal, from any fragment of them. The model was implemented on the SpiNNaker hardware platform using Spiking Neural Networks. A set of experiments based on functional, stress and applicability tests were performed to demonstrate its correct functioning. This work presents the first hardware implementation of a fully-functional bio-inspired spiking hippocampal content-addressable memory model, paving the way for the development of future more complex neuromorphic systems.

Information bottleneck-based Hebbian learning rule naturally ties working memory and synaptic updates

Deep neural feedforward networks are effective models for a wide array of problems, but training and deploying such networks presents a significant energy cost. Spiking neural networks (SNNs), which are modeled after biologically realistic neurons, offer a potential solution when deployed correctly on neuromorphic computing hardware. Still, many applications train SNNs offline, and running network training directly on neuromorphic hardware is an ongoing research problem. The primary hurdle is that back-propagation, which makes training such artificial deep networks possible, is biologically implausible. Neuroscientists are uncertain about how the brain would propagate a precise error signal backward through a network of neurons. Recent progress addresses part of this question, e.g., the weight transport problem, but a complete solution remains intangible. In contrast, novel learning rules based on the information bottleneck (IB) train each layer of a network independently, circumventing the need to propagate errors across layers. Instead, propagation is implicit due the layers' feedforward connectivity. These rules take the form of a three-factor Hebbian update a global error signal modulates local synaptic updates within each layer. Unfortunately, the global signal for a given layer requires processing multiple samples concurrently, and the brain only sees a single sample at a time. We propose a new three-factor update rule where the global signal correctly captures information across samples via an auxiliary memory network. The auxiliary network can be trained a priori independently of the dataset being used with the primary network. We demonstrate comparable performance to baselines on image classification tasks. Interestingly, unlike back-propagation-like schemes where there is no link between learning and memory, our rule presents a direct connection between working memory and synaptic updates. To the best of our knowledge, this is the first rule to make this link explicit. We explore these implications in initial experiments examining the effect of memory capacity on learning performance. Moving forward, this work suggests an alternate view of learning where each layer balances memory-informed compression against task performance. This view naturally encompasses several key aspects of neural computation, including memory, efficiency, and locality.

Spiking neural networks for nonlinear regression

Spiking neural networks (SNN), also often referred to as the third generation of neural networks, carry the potential for a massive reduction in memory and energy consumption over traditional, second-generation neural networks. Inspired by the undisputed efficiency of the human brain, they introduce temporal and neuronal sparsity, which can be exploited by next-generation neuromorphic hardware. Energy efficiency plays a crucial role in many engineering applications, for instance, in structural health monitoring. Machine learning in engineering contexts, especially in data-driven mechanics, focuses on regression. While regression with SNN has already been discussed in a variety of publications, in this contribution, we provide a novel formulation for its accuracy and energy efficiency. In particular, a network topology for decoding binary spike trains to real numbers is introduced, using the membrane potential of spiking neurons. Several different spiking neural architectures, ranging from simple spiking feed-forward to complex spiking long short-term memory neural networks, are derived. Since the proposed architectures do not contain any dense layers, they exploit the full potential of SNN in terms of energy efficiency. At the same time, the accuracy of the proposed SNN architectures is demonstrated by numerical examples, namely different material models. Linear and nonlinear, as well as history-dependent material models, are examined. While this contribution focuses on mechanical examples, the interested reader may regress any custom function by adapting the published source code.

Exploring Flip Flop memories and beyond: training Recurrent Neural Networks with key insights

Training neural networks to perform different tasks is relevant across various disciplines. In particular, Recurrent Neural Networks (RNNs) are of great interest in Computational Neuroscience. Open-source frameworks dedicated to Machine Learning, such as Tensorflow and Keras have produced significant changes in the development of technologies that we currently use. This work contributes by comprehensively investigating and describing the application of RNNs for temporal processing through a study of a 3-bit Flip Flop memory implementation. We delve into the entire modeling process, encompassing equations, task parametrization, and software development. The obtained networks are meticulously analyzed to elucidate dynamics, aided by an array of visualization and analysis tools. Moreover, the provided code is versatile enough to facilitate the modeling of diverse tasks and systems. Furthermore, we present how memory states can be efficiently stored in the vertices of a cube in the dimensionally reduced space, supplementing previous results with a distinct approach.

SLoN: a spiking looming perception network exploiting neural encoding and processing in ON/OFF channels

Looming perception, the ability to sense approaching objects, is crucial for the survival of humans and animals. After hundreds of millions of years of evolutionary development, biological entities have evolved efficient and robust looming perception visual systems. However, current artificial vision systems fall short of such capabilities. In this study, we propose a novel spiking neural network for looming perception that mimics biological vision to communicate motion information through action potentials or spikes, providing a more realistic approach than previous artificial neural networks based on sum-then-activate operations. The proposed spiking looming perception network (SLoN) comprises three core components. Neural encoding, known as phase coding, transforms video signals into spike trains, introducing the concept of phase delay to depict the spatial-temporal competition between phasic excitatory and inhibitory signals shaping looming selectivity. To align with biological substrates where visual signals are bifurcated into parallel ON/OFF channels encoding brightness increments and decrements separately to achieve specific selectivity to ON/OFF-contrast stimuli, we implement eccentric down-sampling at the entrance of ON/OFF channels, mimicking the foveal region of the mammalian receptive field with higher acuity to motion, computationally modeled with a leaky integrate-and-fire (LIF) neuronal network. The SLoN model is deliberately tested under various visual collision scenarios, ranging from synthetic to real-world stimuli. A notable achievement is that the SLoN selectively spikes for looming features concealed in visual streams against other categories of movements, including translating, receding, grating, and near misses, demonstrating robust selectivity in line with biological principles. Additionally, the efficacy of the ON/OFF channels, the phase coding with delay, and the eccentric visual processing are further investigated to demonstrate their effectiveness in looming perception. The cornerstone of this study rests upon showcasing a new paradigm for looming perception that is more biologically plausible in light of biological motion perception.

A review of machine learning and deep learning algorithms for Parkinson's disease detection using handwriting and voice datasets

Parkinson's Disease (PD) is a prevalent neurodegenerative disorder with significant clinical implications. Early and accurate diagnosis of PD is crucial for timely intervention and personalized treatment. In recent years, Machine Learning (ML) and Deep Learning (DL) techniques have emerged as promis-ing tools for improving PD diagnosis. This review paper presents a detailed analysis of the current state of ML and DL-based PD diagnosis, focusing on voice, handwriting, and wave spiral datasets. The study also evaluates the effectiveness of various ML and DL algorithms, including classifiers, on these datasets and highlights their potential in enhancing diagnostic accuracy and aiding clinical decision-making. Additionally, the paper explores the identifi-cation of biomarkers using these techniques, offering insights into improving the diagnostic process. The discussion encompasses different data formats and commonly employed ML and DL methods in PD diagnosis, providing a comprehensive overview of the field. This review serves as a roadmap for future research, guiding the development of ML and DL-based tools for PD detection. It is expected to benefit both the scientific community and medical practitioners by advancing our understanding of PD diagnosis and ultimately improving patient outcomes.

Bidirectional feature pyramid attention-based temporal convolutional network model for motor imagery electroencephalogram classification

Introduction

As an interactive method gaining popularity, brain-computer interfaces (BCIs) aim to facilitate communication between the brain and external devices. Among the various research topics in BCIs, the classification of motor imagery using electroencephalography (EEG) signals has the potential to greatly improve the quality of life for people with disabilities.

Methods

This technology assists them in controlling computers or other devices like prosthetic limbs, wheelchairs, and drones. However, the current performance of EEG signal decoding is not sufficient for real-world applications based on Motor Imagery EEG (MI-EEG). To address this issue, this study proposes an attention-based bidirectional feature pyramid temporal convolutional network model for the classification task of MI-EEG. The model incorporates a multi-head self-attention mechanism to weigh significant features in the MI-EEG signals. It also utilizes a temporal convolution network (TCN) to separate high-level temporal features. The signals are enhanced using the sliding-window technique, and channel and time-domain information of the MI-EEG signals is extracted through convolution.

Results

Additionally, a bidirectional feature pyramid structure is employed to implement attention mechanisms across different scales and multiple frequency bands of the MI-EEG signals. The performance of our model is evaluated on the BCI Competition IV-2a dataset and the BCI Competition IV-2b dataset, and the results showed that our model outperformed the state-of-the-art baseline model, with an accuracy of 87.5 and 86.3% for the subject-dependent, respectively.

Discussion

In conclusion, the BFATCNet model offers a novel approach for EEG-based motor imagery classification in BCIs, effectively capturing relevant features through attention mechanisms and temporal convolutional networks. Its superior performance on the BCI Competition IV-2a and IV-2b datasets highlights its potential for real-world applications. However, its performance on other datasets may vary, necessitating further research on data augmentation techniques and integration with multiple modalities to enhance interpretability and generalization. Additionally, reducing computational complexity for real-time applications is an important area for future work.

Adaptive class augmented prototype network for few-shot relation extraction

Relation extraction is one of the most essential tasks of knowledge construction, but it depends on a large amount of annotated data corpus. Few-shot relation extraction is proposed as a new paradigm, which is designed to learn new relationships between entities with merely a small number of annotated instances, effectively mitigating the cost of large-scale annotation and long-tail problems. To generalize to novel classes not included in the training set, existing approaches mainly focus on tuning pre-trained language models with relation instructions and developing class prototypes based on metric learning to extract relations. However, the learned representations are extremely sensitive to discrepancies in intra-class and inter-class relationships and hard to adaptively classify the relations due to biased class features and spurious correlations, such as similar relation classes having closer inter-class prototype representation. In this paper, we introduce an adaptive class augmented prototype network with instance-level and representation-level augmented mechanisms to strengthen the representation space. Specifically, we design the adaptive class augmentation mechanism to expand the representation of classes in instance-level augmentation, and class augmented representation learning with Bernoulli perturbation context attention to enhance the representation of class features in representation-level augmentation and explore adaptive debiased contrastive learning to train the model. Experimental results have been demonstrated on FewRel and NYT-25 under various few-shot settings, and the proposed model has improved accuracy and generalization, especially for cross-domain and different hard tasks.

Graph-based methods coupled with specific distributional distances for adversarial attack detection

Artificial neural networks are prone to being fooled by carefully perturbed inputs which cause an egregious misclassification. These adversarial attacks have been the focus of extensive research. Likewise, there has been an abundance of research in ways to detect and defend against them. We introduce a novel approach of detection and interpretation of adversarial attacks from a graph perspective. For an input image, we compute an associated sparse graph using the layer-wise relevance propagation algorithm (Bach et al., 2015). Specifically, we only keep edges of the neural network with the highest relevance values. Three quantities are then computed from the graph which are then compared against those computed from the training set. The result of the comparison is a classification of the image as benign or adversarial. To make the comparison, two classification methods are introduced: (1) an explicit formula based on Wasserstein distance applied to the degree of node and (2) a logistic regression. Both classification methods produce strong results which lead us to believe that a graph-based interpretation of adversarial attacks is valuable.

Monitoring time domain characteristics of Parkinson's disease using 3D memristive neuromorphic system

Introduction

Parkinson's disease (PD) is a neurodegenerative disorder affecting millions of patients. Closed-Loop Deep Brain Stimulation (CL-DBS) is a therapy that can alleviate the symptoms of PD. The CL-DBS system consists of an electrode sending electrical stimulation signals to a specific region of the brain and a battery-powered stimulator implanted in the chest. The electrical stimuli in CL-DBS systems need to be adjusted in real-time in accordance with the state of PD symptoms. Therefore, fast and precise monitoring of PD symptoms is a critical function for CL-DBS systems. However, the current CL-DBS techniques suffer from high computational demands for real-time PD symptom monitoring, which are not feasible for implanted and wearable medical devices.

Methods

In this paper, we present an energy-efficient neuromorphic PD symptom detector using memristive three-dimensional integrated circuits (3D-ICs). The excessive oscillation at beta frequencies (13-35 Hz) at the subthalamic nucleus (STN) is used as a biomarker of PD symptoms.

Results

Simulation results demonstrate that our neuromorphic PD detector, implemented with an 8-layer spiking Long Short-Term Memory (S-LSTM), excels in recognizing PD symptoms, achieving a training accuracy of 99.74% and a validation accuracy of 99.52% for a 75%-25% data split. Furthermore, we evaluated the improvement of our neuromorphic CL-DBS detector using NeuroSIM. The chip area, latency, energy, and power consumption of our CL-DBS detector were reduced by 47.4%, 66.63%, 65.6%, and 67.5%, respectively, for monolithic 3D-ICs. Similarly, for heterogeneous 3D-ICs, employing memristive synapses to replace traditional Static Random Access Memory (SRAM) resulted in reductions of 44.8%, 64.75%, 65.28%, and 67.7% in chip area, latency, and power usage.

Discussion

This study introduces a novel approach for PD symptom evaluation by directly utilizing spiking signals from neural activities in the time domain. This method significantly reduces the time and energy required for signal conversion compared to traditional frequency domain approaches. The study pioneers the use of neuromorphic computing and memristors in designing CL-DBS systems, surpassing SRAM-based designs in chip design area, latency, and energy efficiency. Lastly, the proposed neuromorphic PD detector demonstrates high resilience to timing variations in brain neural signals, as confirmed by robustness analysis.

Neurorobotic reinforcement learning for domains with parametrical uncertainty

Neuromorphic hardware paired with brain-inspired learning strategies have enormous potential for robot control. Explicitly, these advantages include low energy consumption, low latency, and adaptability. Therefore, developing and improving learning strategies, algorithms, and neuromorphic hardware integration in simulation is a key to moving the state-of-the-art forward. In this study, we used the neurorobotics platform (NRP) simulation framework to implement spiking reinforcement learning control for a robotic arm. We implemented a force-torque feedback-based classic object insertion task ("peg-in-hole") and controlled the robot for the first time with neuromorphic hardware in the loop. We therefore provide a solution for training the system in uncertain environmental domains by using randomized simulation parameters. This leads to policies that are robust to real-world parameter variations in the target domain, filling the sim-to-real gap.To the best of our knowledge, it is the first neuromorphic implementation of the peg-in-hole task in simulation with the neuromorphic Loihi chip in the loop, and with scripted accelerated interactive training in the Neurorobotics Platform, including randomized domains.

Gradient-based feature-attribution explainability methods for spiking neural networks

Introduction

Spiking neural networks (SNNs) are a model of computation that mimics the behavior of biological neurons. SNNs process event data (spikes) and operate more sparsely than artificial neural networks (ANNs), resulting in ultra-low latency and small power consumption. This paper aims to adapt and evaluate gradient-based explainability methods for SNNs, which were originally developed for conventional ANNs.

Methods

The adapted methods aim to create input feature attribution maps for SNNs trained through backpropagation that process either event-based spiking data or real-valued data. The methods address the limitations of existing work on explainability methods for SNNs, such as poor scalability, limited to convolutional layers, requiring the training of another model, and providing maps of activation values instead of true attribution scores. The adapted methods are evaluated on classification tasks for both real-valued and spiking data, and the accuracy of the proposed methods is confirmed through perturbation experiments at the pixel and spike levels.

Results and discussion

The results reveal that gradient-based SNN attribution methods successfully identify highly contributing pixels and spikes with significantly less computation time than model-agnostic methods. Additionally, we observe that the chosen coding technique has a noticeable effect on the input features that will be most significant. These findings demonstrate the potential of gradient-based explainability methods for SNNs in improving our understanding of how these networks process information and contribute to the development of more efficient and accurate SNNs.

ALBSNN: ultra-low latency adaptive local binary spiking neural network with accuracy loss estimator

Spiking neural network (SNN) is a brain-inspired model with more spatio-temporal information processing capacity and computational energy efficiency. However, with the increasing depth of SNNs, the memory problem caused by the weights of SNNs has gradually attracted attention. In this study, we propose an ultra-low latency adaptive local binary spiking neural network (ALBSNN) with accuracy loss estimators, which dynamically selects the network layers to be binarized to ensure a balance between quantization degree and classification accuracy by evaluating the error caused by the binarized weights during the network learning process. At the same time, to accelerate the training speed of the network, the global average pooling (GAP) layer is introduced to replace the fully connected layers by combining convolution and pooling. Finally, to further reduce the error caused by the binary weight, we propose binary weight optimization (BWO), which updates the overall weight by directly adjusting the binary weight. This method further reduces the loss of the network that reaches the training bottleneck. The combination of the above methods balances the network's quantization and recognition ability, enabling the network to maintain the recognition capability equivalent to the full precision network and reduce the storage space by more than 20%. So, SNNs can use a small number of time steps to obtain better recognition accuracy. In the extreme case of using only a one-time step, we still can achieve 93.39, 92.12, and 69.55% testing accuracy on three traditional static datasets, Fashion- MNIST, CIFAR-10, and CIFAR-100, respectively. At the same time, we evaluate our method on neuromorphic N-MNIST, CIFAR10-DVS, and IBM DVS128 Gesture datasets and achieve advanced accuracy in SNN with binary weights. Our network has greater advantages in terms of storage resources and training time.

Ring attractor bio-inspired neural network for social robot navigation

Introduction

We introduce a bio-inspired navigation system for a robot to guide a social agent to a target location while avoiding static and dynamic obstacles. Robot navigation can be accomplished through a model of ring attractor neural networks. This connectivity pattern between neurons enables the generation of stable activity patterns that can represent continuous variables such as heading direction or position. The integration of sensory representation, decision-making, and motor control through ring attractor networks offers a biologically-inspired approach to navigation in complex environments.

Methods

The navigation system is divided into perception, planning, and control stages. Our approach is compared to the widely-used Social Force Model and Rapidly Exploring Random Tree Star methods using the Social Individual Index and Relative Motion Index as metrics in simulated experiments. We created a virtual scenario of a pedestrian area with various obstacles and dynamic agents.

Results

The results obtained in our experiments demonstrate the effectiveness of this architecture in guiding a social agent while avoiding obstacles, and the metrics used for evaluating the system indicate that our proposal outperforms the widely used Social Force Model.

Discussion

Our approach points to improving safety and comfort specifically for human-robot interactions. By integrating the Social Individual Index and Relative Motion Index, this approach considers both social comfort and collision avoidance features, resulting in better human-robot interactions in a crowded environment.

Exploring spiking neural networks: a comprehensive analysis of mathematical models and applications

This article presents a comprehensive analysis of spiking neural networks (SNNs) and their mathematical models for simulating the behavior of neurons through the generation of spikes. The study explores various models, including LIF and NLIF, for constructing SNNs and investigates their potential applications in different domains. However, implementation poses several challenges, including identifying the most appropriate model for classification tasks that demand high accuracy and low-performance loss. To address this issue, this research study compares the performance, behavior, and spike generation of multiple SNN models using consistent inputs and neurons. The findings of the study provide valuable insights into the benefits and challenges of SNNs and their models, emphasizing the significance of comparing multiple models to identify the most effective one. Moreover, the study quantifies the number of spiking operations required by each model to process the same inputs and produce equivalent outputs, enabling a thorough assessment of computational efficiency. The findings provide valuable insights into the benefits and limitations of SNNs and their models. The research underscores the significance of comparing different models to make informed decisions in practical applications. Additionally, the results reveal essential variations in biological plausibility and computational efficiency among the models, further emphasizing the importance of selecting the most suitable model for a given task. Overall, this study contributes to a deeper understanding of SNNs and offers practical guidelines for using their potential in real-world scenarios.

Learning cortical hierarchies with temporal Hebbian updates

A key driver of mammalian intelligence is the ability to represent incoming sensory information across multiple abstraction levels. For example, in the visual ventral stream, incoming signals are first represented as low-level edge filters and then transformed into high-level object representations. Similar hierarchical structures routinely emerge in artificial neural networks (ANNs) trained for object recognition tasks, suggesting that similar structures may underlie biological neural networks. However, the classical ANN training algorithm, backpropagation, is considered biologically implausible, and thus alternative biologically plausible training methods have been developed such as Equilibrium Propagation, Deep Feedback Control, Supervised Predictive Coding, and Dendritic Error Backpropagation. Several of those models propose that local errors are calculated for each neuron by comparing apical and somatic activities. Notwithstanding, from a neuroscience perspective, it is not clear how a neuron could compare compartmental signals. Here, we propose a solution to this problem in that we let the apical feedback signal change the postsynaptic firing rate and combine this with a differential Hebbian update, a rate-based version of classical spiking time-dependent plasticity (STDP). We prove that weight updates of this form minimize two alternative loss functions that we prove to be equivalent to the error-based losses used in machine learning: the inference latency and the amount of top-down feedback necessary. Moreover, we show that the use of differential Hebbian updates works similarly well in other feedback-based deep learning frameworks such as Predictive Coding or Equilibrium Propagation. Finally, our work removes a key requirement of biologically plausible models for deep learning and proposes a learning mechanism that would explain how temporal Hebbian learning rules can implement supervised hierarchical learning.

BalanceHRNet: An effective network for bottom-up human pose estimation

In the study of human pose estimation, which is widely used in safety and sports scenes, the performance of deep learning methods is greatly reduced in high overlap rate and crowded scenes. Therefore, we propose a bottom-up model, called BalanceHRNet, which is based on balanced high-resolution module and a new branch attention module. BalanceHRNet draws on the multi-branch structure and fusion method of a popular model HigherHRNet. And our model overcomes the shortcoming of HigherHRNet that cannot obtain a large enough receptive field. Specifically, through the connecting structure in balanced high-resolution module, we can connect almost all convolutional layers and obtain a sufficiently large receptive field. At the same time, the multi-resolution representation can be maintained due to the use of balanced high-resolution module, which enable our model to recognize objects with richer scales and obtain more complex semantics information. And for branch fusion method, we design branch attention to obtain the importance of different branches at different stages. Finally, our model improves the accuracy while ensuring a smaller amount of computation than HigherHRNet. The CrowdPose dataset is used as test dataset, and HigherHRNet, AlphaPose, OpenPose and so on are taken as comparison models. The AP measured by BalanceHRNet is 63.0%, increased by 3.1% compared to best model - HigherHRNet. We also demonstrate the effectiveness of our network through the COCO(2017) keypoint detection dataset. Compared with HigherHRNet-w32, the AP of our model is improved by 1.6%.

Robust data hiding for JPEG images with invertible neural network

JPEG compression will cause severe distortion to the shared compressed image, which brings great challenges to extracting messages correctly from the stego image. To address such challenges, we propose a novel end-to-end robust data hiding scheme for JPEG images. The embedding and extracting secret messages on the quantized discrete cosine transform (DCT) coefficients are implemented by the bi-directional process of the invertible neural network (INN), which can provide intrinsic robustness against lossy JPEG compression. We design a JPEG compression attack module to simulate the JPEG compression process, which helps the network automatically learn how to recover the secret message from JPEG compressed image. Experimental results have demonstrated that our method achieves strong robustness against lossy JPEG compression, and also significantly improves the security compared with the existing data hiding methods on the premise of ensuring image quality and high capacity. For example, the detection error of our method against XuNet has been increased by 3.45% over the existing data hiding methods.

Image Watermarking Using Least Significant Bit and Canny Edge Detection

With the advancement in information technology, digital data stealing and duplication have become easier. Over a trillion bytes of data are generated and shared on social media through the internet in a single day, and the authenticity of digital data is currently a major problem. Cryptography and image watermarking are domains that provide multiple security services, such as authenticity, integrity, and privacy. In this paper, a digital image watermarking technique is proposed that employs the least significant bit (LSB) and canny edge detection method. The proposed method provides better security services and it is computationally less expensive, which is the demand of today's world. The major contribution of this method is to find suitable places for watermarking embedding and provides additional watermark security by scrambling the watermark image. A digital image is divided into non-overlapping blocks, and the gradient is calculated for each block. Then convolution masks are applied to find the gradient direction and magnitude, and non-maximum suppression is applied. Finally, LSB is used to embed the watermark in the hysteresis step. Furthermore, additional security is provided by scrambling the watermark signal using our chaotic substitution box. The proposed technique is more secure because of LSB's high payload and watermark embedding feature after a canny edge detection filter. The canny edge gradient direction and magnitude find how many bits will be embedded. To test the performance of the proposed technique, several image processing, and geometrical attacks are performed. The proposed method shows high robustness to image processing and geometrical attacks.

A systematic comparison of deep learning methods for EEG time series analysis

Analyzing time series data like EEG or MEG is challenging due to noisy, high-dimensional, and patient-specific signals. Deep learning methods have been demonstrated to be superior in analyzing time series data compared to shallow learning methods which utilize handcrafted and often subjective features. Especially, recurrent deep neural networks (RNN) are considered suitable to analyze such continuous data. However, previous studies show that they are computationally expensive and difficult to train. In contrast, feed-forward networks (FFN) have previously mostly been considered in combination with hand-crafted and problem-specific feature extractions, such as short time Fourier and discrete wavelet transform. A sought-after are easily applicable methods that efficiently analyze raw data to remove the need for problem-specific adaptations. In this work, we systematically compare RNN and FFN topologies as well as advanced architectural concepts on multiple datasets with the same data preprocessing pipeline. We examine the behavior of those approaches to provide an update and guideline for researchers who deal with automated analysis of EEG time series data. To ensure that the results are meaningful, it is important to compare the presented approaches while keeping the same experimental setup, which to our knowledge was never done before. This paper is a first step toward a fairer comparison of different methodologies with EEG time series data. Our results indicate that a recurrent LSTM architecture with attention performs best on less complex tasks, while the temporal convolutional network (TCN) outperforms all the recurrent architectures on the most complex dataset yielding a 8.61% accuracy improvement. In general, we found the attention mechanism to substantially improve classification results of RNNs. Toward a light-weight and online learning-ready approach, we found extreme learning machines (ELM) to yield comparable results for the less complex tasks.

A brain-inspired robot pain model based on a spiking neural network

Introduction

Pain is a crucial function for organisms. Building a "Robot Pain" model inspired by organisms' pain could help the robot learn self-preservation and extend longevity. Most previous studies about robots and pain focus on robots interacting with people by recognizing their pain expressions or scenes, or avoiding obstacles by recognizing dangerous objects. Robots do not have human-like pain capacity and cannot adaptively respond to danger. Inspired by the evolutionary mechanisms of pain emergence and the Free Energy Principle (FEP) in the brain, we summarize the neural mechanisms of pain and construct a Brain-inspired Robot Pain Spiking Neural Network (BRP-SNN) with spike-time-dependent-plasticity (STDP) learning rule and population coding method.

Methods

The proposed model can quantify machine injury by detecting the coupling relationship between multi-modality sensory information and generating "robot pain" as an internal state.

Results

We provide a comparative analysis with the results of neuroscience experiments, showing that our model has biological interpretability. We also successfully tested our model on two tasks with real robots-the alerting actual injury task and the preventing potential injury task.

Discussion

Our work has two major contributions: (1) It has positive implications for the integration of pain concepts into robotics in the intelligent robotics field. (2) Our summary of pain's neural mechanisms and the implemented computational simulations provide a new perspective to explore the nature of pain, which has significant value for future pain research in the cognitive neuroscience field.

Tuberculous pleural effusion prediction using ant colony optimizer with grade-based search assisted support vector machine

Introduction

Although tuberculous pleural effusion (TBPE) is simply an inflammatory response of the pleura caused by tuberculosis infection, it can lead to pleural adhesions and cause sequelae of pleural thickening, which may severely affect the mobility of the chest cavity.

Methods

In this study, we propose bGACO-SVM, a model with good diagnostic power, for the adjunctive diagnosis of TBPE. The model is based on an enhanced continuous ant colony optimization (ACOR) with grade-based search technique (GACO) and support vector machine (SVM) for wrapped feature selection. In GACO, grade-based search greatly improves the convergence performance of the algorithm and the ability to avoid getting trapped in local optimization, which improves the classification capability of bGACO-SVM.

Results

To test the performance of GACO, this work conducts comparative experiments between GACO and nine basic algorithms and nine state-of-the-art variants as well. Although the proposed GACO does not offer much advantage in terms of time complexity, the experimental results strongly demonstrate the core advantages of GACO. The accuracy of bGACO-predictive SVM was evaluated using existing datasets from the UCI and TBPE datasets.

Discussion

In the TBPE dataset trial, 147 TBPE patients were evaluated using the created bGACO-SVM model, showing that the bGACO-SVM method is an effective technique for accurately predicting TBPE.

Outer-synchronization criterions for asymmetric recurrent time-varying neural networks described by differential-algebraic system via data-sampling principles

Asymmetric recurrent time-varying neural networks (ARTNNs) can enable realistic brain-like models to help scholars explore the mechanisms of the human brain and thus realize the applications of artificial intelligence, whose dynamical behaviors such as synchronization has attracted extensive research interest due to its superior applicability and flexibility. In this paper, we examined the outer-synchronization of ARTNNs, which are described by the differential-algebraic system (DAS). By designing appropriate centralized and decentralized data-sampling approaches which fully account for information gathering at the times tk and tki. Using the characteristics of integral inequalities and the theory of differential equations, several novel suitable outer-synchronization conditions were established. Those conditions facilitate the analysis and applications of dynamical behaviors of ARTNNs. The superiority of the theoretical results was then demonstrated by using a numerical example.

Brain-inspired Predictive Coding Improves the Performance of Machine Challenging Tasks

Backpropagation has been regarded as the most favorable algorithm for training artificial neural networks. However, it has been criticized for its biological implausibility because its learning mechanism contradicts the human brain. Although backpropagation has achieved super-human performance in various machine learning applications, it often shows limited performance in specific tasks. We collectively referred to such tasks as machine-challenging tasks (MCTs) and aimed to investigate methods to enhance machine learning for MCTs. Specifically, we start with a natural question: Can a learning mechanism that mimics the human brain lead to the improvement of MCT performances? We hypothesized that a learning mechanism replicating the human brain is effective for tasks where machine intelligence is difficult. Multiple experiments corresponding to specific types of MCTs where machine intelligence has room to improve performance were performed using predictive coding, a more biologically plausible learning algorithm than backpropagation. This study regarded incremental learning, long-tailed, and few-shot recognition as representative MCTs. With extensive experiments, we examined the effectiveness of predictive coding that robustly outperformed backpropagation-trained networks for the MCTs. We demonstrated that predictive coding-based incremental learning alleviates the effect of catastrophic forgetting. Next, predictive coding-based learning mitigates the classification bias in long-tailed recognition. Finally, we verified that the network trained with predictive coding could correctly predict corresponding targets with few samples. We analyzed the experimental result by drawing analogies between the properties of predictive coding networks and those of the human brain and discussing the potential of predictive coding networks in general machine learning.

Extended liquid state machines for speech recognition

A liquid state machine (LSM) is a biologically plausible model of a cortical microcircuit. It exists of a random, sparse reservoir of recurrently connected spiking neurons with fixed synapses and a trainable readout layer. The LSM exhibits low training complexity and enables backpropagation-free learning in a powerful, yet simple computing paradigm. In this work, the liquid state machine is enhanced by a set of bio-inspired extensions to create the extended liquid state machine (ELSM), which is evaluated on a set of speech data sets. Firstly, we ensure excitatory/inhibitory (E/I) balance to enable the LSM to operate in edge-of-chaos regime. Secondly, spike-frequency adaptation (SFA) is introduced in the LSM to improve the memory capabilities. Lastly, neuronal heterogeneity, by means of a differentiation in time constants, is introduced to extract a richer dynamical LSM response. By including E/I balance, SFA, and neuronal heterogeneity, we show that the ELSM consistently improves upon the LSM while retaining the benefits of the straightforward LSM structure and training procedure. The proposed extensions led up to an 5.2% increase in accuracy while decreasing the number of spikes in the ELSM up to 20.2% on benchmark speech data sets. On some benchmarks, the ELSM can even attain similar performances as the current state-of-the-art in spiking neural networks. Furthermore, we illustrate that the ELSM input-liquid and recurrent synaptic weights can be reduced to 4-bit resolution without any significant loss in classification performance. We thus show that the ELSM is a powerful, biologically plausible and hardware-friendly spiking neural network model that can attain near state-of-the-art accuracy on speech recognition benchmarks for spiking neural networks.

Quality improvement of undergraduate courses based on fuzzy analytic hierarchy process and entropy method

Since the curriculum is the core carrier to improve the level of talent cultivation in colleges and universities, strengthening the reform of course teaching and improving the quality of course teaching are fundamental to the survival and development of colleges and universities, and also an important part of higher education reform. In this study, a fuzzy analytic hierarchy process (AHP) and an entropy method were used to determine the weight of the core evaluation indicators of undergraduate course quality improvement, including four first-level indicators of the curriculum concept, curriculum resources, curriculum organization, and curriculum effectiveness, and 12 s-level evaluation indicators and weights. Then, based on a case study of the first-class undergraduate course “Management” of Anyang Normal University, the way to evaluate the course by the AHP and entropy method was explained. Finally, according to the evaluation results, the ideas of course construction were put forward, such as changing the course concept, enriching the course resources, paying attention to the course organization, and ensuring the course effectiveness, so as to improve the quality of undergraduate courses and also to improve the quality of undergraduate talent training with the improvement of course quality as the starting point.

UAV Localization Algorithm Based on Factor Graph Optimization in Complex Scenes

With the increasingly widespread application of UAV intelligence, the need for autonomous navigation and positioning is becoming more and more important. To solve the problem that UAV cannot perform localization in complex scenes, a new multi-source fusion framework factor graph optimization algorithm is used for UAV localization state estimation in this paper, which is based on IMU/GNSS/VO multi-source sensors. Based on the factor graph model and the iSAM incremental inference algorithm, a multi-source fusion model of IMU/GNSS/VO is established, including the IMU pre-integration factor, IMU bias factor, GNSS factor, and VO factor. Mathematical simulations and validations on the EuRoC dataset show that, when the selected sliding window size is 30, the factor graph optimization (FGO) algorithm can not only meet the requirements of real time and accuracy at the same time, but it also achieves a plug-and-play function in the event of local sensor failures. Finally, compared with the traditional federated Kalman algorithm and the adaptive federated Kalman algorithm, the positioning accuracy of the FGO algorithm in this paper is improved by 1.5-2-fold, and can effectively improve autonomous navigation system robustness and flexibility in complex scenarios. Moreover, the multi-source fusion framework in this paper is a general algorithm framework that can satisfy other scenarios and other types of sensor combinations.

An Automated Approach for the Detection of Alzheimer's Disease From Resting State Electroencephalography

Early detection is crucial to control the progression of Alzheimer's disease and to postpone intellectual decline. Most current detection techniques are costly, inaccessible, or invasive. Furthermore, they require laborious analysis, what delays the start of medical treatment. To overcome this, researchers have recently investigated AD detection based on electroencephalography, a non-invasive neurophysiology technique, and machine learning algorithms. However, these approaches typically rely on manual procedures such as visual inspection, that requires additional personnel for the analysis, or on cumbersome EEG acquisition systems. In this paper, we performed a preliminary evaluation of a fully-automated approach for AD detection based on a commercial EEG acquisition system and an automated classification pipeline. For this purpose, we recorded the resting state brain activity of 26 participants from three groups: mild AD, mild cognitive impairment (MCI-non-AD), and healthy controls. First, we applied automated data-driven algorithms to reject EEG artifacts. Then, we obtained spectral, complexity, and entropy features from the preprocessed EEG segments. Finally, we assessed two binary classification problems: mild AD vs. controls, and MCI-non-AD vs. controls, through leave-one-subject-out cross-validation. The preliminary results that we obtained are comparable to the best reported in literature, what suggests that AD detection could be automatically detected through automated processing and commercial EEG systems. This is promising, since it may potentially contribute to reducing costs related to AD screening, and to shortening detection times, what may help to advance medical treatment.

Bio-Inspired Autonomous Learning Algorithm With Application to Mobile Robot Obstacle Avoidance

Spiking Neural Networks (SNNs) are often considered the third generation of Artificial Neural Networks (ANNs), owing to their high information processing capability and the accurate simulation of biological neural network behaviors. Though the research for SNNs has been quite active in recent years, there are still some challenges to applying SNNs to various potential applications, especially for robot control. In this study, a biologically inspired autonomous learning algorithm based on reward modulated spike-timing-dependent plasticity is proposed, where a novel rewarding generation mechanism is used to generate the reward signals for both learning and decision-making processes. The proposed learning algorithm is evaluated by a mobile robot obstacle avoidance task and experimental results show that the mobile robot with the proposed algorithm exhibits a good learning ability. The robot can successfully avoid obstacles in the environment after some learning trials. This provides an alternative method to design and apply the bio-inspired robot with autonomous learning capability in the typical robotic task scenario.

Transient Response and Firing Behaviors of Memristive Neuron Circuit

The signal transmission mechanism of the Resistor-Capacitor (RC) circuit is similar to the intracellular and extracellular signal propagating mechanism of the neuron. Thus, the RC circuit can be utilized as the circuit model of the neuron cell membrane. However, resistors are electronic components with the fixed-resistance and have no memory properties. A memristor is a promising neuro-morphological electronic device with nonvolatile, switching, and nonlinear characteristics. First of all, we consider replacing the resistor in the RC neuron circuit with a memristor, which is named the Memristor-Capacitor (MC) circuit, then the MC neuron model is constructed. We compare the charging and discharging processes between the RC and MC neuron circuits. Secondly, two models are compared under the different external stimuli. Finally, the synchronous and asynchronous activities of the RC and MC neuron circuits are performed. Extensive experimental results suggest that the charging and discharging speed of the MC neuron circuit is faster than that of the RC neuron circuit. Given sufficient time and proper external stimuli, the RC and MC neuron circuits can produce the action potentials. The synchronous and asynchronous phenomena in the two neuron circuits reproduce nonlinear dynamic behaviors of the biological neurons.

Optimal Demand-Side Management Using Flat Pricing Scheme in Smart Grid

This work proposes a framework to solve demand-side management (DSM) problem by systematically scheduling energy consumption using flat pricing scheme (FPS) in smart grid (SG). The framework includes microgrid with renewable energy sources (solar and wind), energy storage systems, electric vehicles (EVs), and building appliances like time flexible, power flexible, and base/critical appliances. For the proposed framework, we develop an ant colony optimization (ACO) algorithm, which efficiently schedules smart appliances, and EVs batteries charging/discharging with microgrid and without (W/O) microgrid under FPS to minimize energy cost, carbon emission, and peak to average ratio (PAR). An integrated technique of enhanced differential evolution (EDE) algorithm and artificial neural network (ANN) is devised to predict solar irradiance and wind speed for accurate microgrid energy estimation. To endorse the applicability of the proposed framework, simulations are conducted. Moreover, the proposed framework based on the ACO algorithm is compared to mixed-integer linear programming (MILP) and W/O scheduling energy management frameworks in terms of energy cost, carbon emission, and PAR. The developed ACO algorithm reduces energy cost, PAR, and carbon emission by 23.69%, 26.20%, and 15.35% in scenario I, and 25.09%, 31.45%, and 18.50% in scenario II, respectively, as compared to W/O scheduling case. The results affirm the applicability of the proposed framework in aspects of the desired objectives.

Graph regularized spatial-spectral subspace clustering for hyperspectral band selection

Hyperspectral band selection, which aims to select a small number of bands to reduce data redundancy and noisy bands, has attracted widespread attention in recent years. Many effective clustering-based band selection methods have been proposed to accomplish the band selection task and have achieved satisfying performance. However, most of the previous methods reshape the original hyperspectral images (HSIs) into a set of stretched band vectors, which ignore the spatial information of HSIs and the difference between diverse regions. To address these issues, a graph regularized spatial-spectral subspace clustering method for hyperspectral band selection is proposed in this paper, referred to as GRSC. Specifically, the proposed method adopts superpixel segmentation to preserve the spatial information of HSIs by segmenting their first principal component into diverse homogeneous regions. Then the discriminative latent features are generated from each segmented region to represent the whole band, which can mitigate the effect of noise on the band selection. Finally, a self-representation subspace clustering model and an l_2,1-norm regularization are utilized to explore the spectral correlation among all bands. In addition, a similarity graph between region-aware latent features is adaptively learned to preserve the spatial structure of HSIs in the latent representation space. Extensive classification experimental results on three public datasets verify the effectiveness of GRSC over several state-of-the-art methods. The demo code of this work is publicly available at https://github.com/WangJun2023/GRSC.

Analytical Treatment of Unsteady Fluid Flow of Nonhomogeneous Nanofluids among Two Infinite Parallel Surfaces: Collocation Method-Based Study

Fluid flow and heat transfer of nanofluids have gained a lot of attention due to their wide application in industry. In this context, the appropriate solution to such phenomena is the study of this exciting and challenging field by the research community. This paper presents an extension of a well-known collocation method (CM) to investigate the accurate solutions to unsteady flow and heat transfer among two parallel plates. First, a mathematical model is developed for the discussed phenomena, then this model is converted into a non-dimensional form using viable similarity variables. In order to inspect the accurate solutions of the accomplished set of nonlinear ordinary differential equations, a collocation method is proposed and applied successfully. Various simulations are performed to analyze the behavior of non-dimensional velocity, temperature, and concentration profiles alongside the deviation of physical parameters present in the model, and then plotted graphically. It is important to mention that the velocity is enhanced due to the higher impact of the parameter Ha. The parameter Nt caused an efficient enhancement in the temperature distribution while the parameters Nt provided a drop in the temperature that actually affected the rate of heat transmission. Dual behavior of concentration is noted for parameter b, while it can be noted that mixed increasing behavior is available for the concentration against Le. The behavior of skin friction, the Nusselt number, and the Sherwood number were also investigated in addition to the physical parameters. It was observed that the Nusselt number increases with the enhancement of the effects of the magnetic field parameter and the Prandtl number. A comparative study shows that the proposed scheme is very effective and reliable in investigating the solutions of the discussed phenomena and can be extended to find the solutions to more nonlinear physical problems with complex geometry.

Combining Optical Coherence Tomography and Fundus Photography to Improve Glaucoma Screening

We aimed to evaluate the accuracy of glaucoma screening using fundus photography combined with optical coherence tomography and determine the agreement between ophthalmologists and ophthalmology residents. We used a comprehensive ophthalmologic examination dataset obtained from 503 cases (1006 eyes). Of the 1006 eyes, 132 had a confirmed glaucoma diagnosis. Overall, 24 doctors, comprising two groups (ophthalmologists and ophthalmology residents, 12 individuals/group), analyzed the data presented in three screening strategies as follows: (1) fundus photography alone, (2) fundus photography + optical coherence tomography, and (3) fundus photography + optical coherence tomography + comprehensive examination. We investigated the diagnostic accuracy (sensitivity and specificity). The respective sensitivity and specificity values for the diagnostic accuracy obtained by 24 doctors, 12 ophthalmologists, and 12 ophthalmology residents were as follows: (1) fundus photography: sensitivity, 55.4%, 55.4%, and 55.4%; specificity, 91.8%, 94.0%, and 89.6%; (2) fundus photography + OCT: sensitivity, 80.0%, 82.3%, and 77.8%; specificity, 91.7%, 92.9%, and 90.6%; and (3) fundus photography + OCT + comprehensive examination: sensitivity 78.4%, 79.8%, and 77.1%; specificity, 92.7%, 94.0%, and 91.3%. The diagnostic accuracy of glaucoma screening significantly increased with optical coherence tomography. Following its addition, ophthalmologists could more effectively improve the diagnostic accuracy than ophthalmology residents. Screening accuracy is improved when optical coherence tomography is added to fundus photography.