Brain-inspired global-local learning incorporated with neuromorphic computing

SemiSynBio: A new era for neuromorphic computing

Neuromorphic computing has the potential to achieve the requirements of the next-generation artificial intelligence (AI) systems, due to its advantages of adaptive learning and parallel computing. Meanwhile, biocomputing has seen ongoing development with the rise of synthetic biology, becoming the driving force for new generation semiconductor synthetic biology (SemiSynBio) technologies. DNA-based biomolecules could potentially perform the functions of Boolean operators as logic gates and be used to construct artificial neural networks (ANNs), providing the possibility of executing neuromorphic computing at the molecular level. Herein, we briefly outline the principles of neuromorphic computing, describe the advances in DNA computing with a focus on synthetic neuromorphic computing, and summarize the major challenges and prospects for synthetic neuromorphic computing. We believe that constructing such synthetic neuromorphic circuits will be an important step toward realizing neuromorphic computing, which would be of widespread use in biocomputing, DNA storage, information security, and national defense.

An Ion-Mediated Spiking Chemical Neuron based on Mott Memristor

Artificial spiking neurons capable of interpreting ionic information into electrical spikes are critical to mimic biological signaling systems. Mott memristors are attractive for constructing artificial spiking neurons due to their simple structure, low energy consumption, and rich neural dynamics. However, challenges remain in achieving ion-mediated spiking and biohybrid-interfacing in Mott neurons. Here, a biomimetic spiking chemical neuron (SCN) utilizing an NbOx Mott memristor and oxide field-effect transistor-type chemical sensor is introduced. The SCN exhibits both excitation and inhibition spiking behaviors toward ionic concentrations akin to biological neural systems. It demonstrates spiking responses across physiological and pathological Na+ concentrations (1-200 × 10-3 m). The Na+-mediated SCN enables both frequency encoding and time-to-first-spike coding schemes, illustrating the rich neural dynamics of Mott neuron. In addition, the SCN interfaced with L929 cells facilitates real-time modulation of ion-mediated spiking under both normal and salty cellular microenvironments.

Brain-inspired chaotic spiking backpropagation

Spiking neural networks (SNNs) have superior energy efficiency due to their spiking signal transmission, which mimics biological nervous systems, but they are difficult to train effectively. Although surrogate gradient-based methods offer a workable solution, trained SNNs frequently fall into local minima because they are still primarily based on gradient dynamics. Inspired by the chaotic dynamics in animal brain learning, we propose a chaotic spiking backpropagation (CSBP) method that introduces a loss function to generate brain-like chaotic dynamics and further takes advantage of the ergodic and pseudo-random nature to make SNN learning effective and robust. From a computational viewpoint, we found that CSBP significantly outperforms current state-of-the-art methods on both neuromorphic data sets (e.g. DVS-CIFAR10 and DVS-Gesture) and large-scale static data sets (e.g. CIFAR100 and ImageNet) in terms of accuracy and robustness. From a theoretical viewpoint, we show that the learning process of CSBP is initially chaotic, then subject to various bifurcations and eventually converges to gradient dynamics, consistently with the observation of animal brain activity. Our work provides a superior core tool for direct SNN training and offers new insights into understanding the learning process of a biological brain.

Proto-neural networks from thermal proteins

Proteinoids are synthetic polymers that have structural similarities to natural proteins, and their formation is achieved through the application of heat to amino acid combinations in a dehydrated environment. The thermal proteins, initially synthesised by Sidney Fox during the 1960s, has the ability to undergo self-assembly, resulting in the formation of microspheres that resemble cells. These microspheres have fascinating biomimetic characteristics. In recent studies, substantial advancements have been made in elucidating the electrical signalling phenomena shown by proteinoids, hence showcasing their promising prospects in the field of neuro-inspired computing. This study demonstrates the advancement of experimental prototypes that employ proteinoids in the construction of fundamental neural network structures. The article provides an overview of significant achievements in proteinoid systems, such as the demonstration of electrical excitability, emulation of synaptic functions, capabilities in pattern recognition, and adaptability of network structures. This study examines the similarities and differences between proteinoid networks and spontaneous neural computation. We examine the persistent challenges associated with deciphering the underlying mechanisms of emergent proteinoid-based intelligence. Additionally, we explore the potential for developing bio-inspired computing systems using synthetic thermal proteins in forthcoming times. The results of this study offer a theoretical foundation for the advancement of adaptive, self-assembling electronic systems that operate using artificial bio-neural principles.

Advancing brain-inspired computing with hybrid neural networks

Brain-inspired computing, drawing inspiration from the fundamental structure and information-processing mechanisms of the human brain, has gained significant momentum in recent years. It has emerged as a research paradigm centered on brain-computer dual-driven and multi-network integration. One noteworthy instance of this paradigm is the hybrid neural network (HNN), which integrates computer-science-oriented artificial neural networks (ANNs) with neuroscience-oriented spiking neural networks (SNNs). HNNs exhibit distinct advantages in various intelligent tasks, including perception, cognition and learning. This paper presents a comprehensive review of HNNs with an emphasis on their origin, concepts, biological perspective, construction framework and supporting systems. Furthermore, insights and suggestions for potential research directions are provided aiming to propel the advancement of the HNN paradigm.

Memristor-Based Artificial Chips

Memristors, promising nanoelectronic devices with in-memory resistive switching behavior that is assembled with a physically integrated core processing unit (CPU) and memory unit and even possesses highly possible multistate electrical behavior, could avoid the von Neumann bottleneck of traditional computing devices and show a highly efficient ability of parallel computation and high information storage. These advantages position them as potential candidates for future data-centric computing requirements and add remarkable vigor to the research of next-generation artificial intelligence (AI) systems, particularly those that involve brain-like intelligence applications. This work provides an overview of the evolution of memristor-based devices, from their initial use in creating artificial synapses and neural networks to their application in developing advanced AI systems and brain-like chips. It offers a broad perspective of the key device primitives enabling their special applications from the view of materials, nanostructure, and mechanism models. We highlight these demonstrations of memristor-based nanoelectronic devices that have potential for use in the field of brain-like AI, point out the existing challenges of memristor-based nanodevices toward brain-like chips, and propose the guiding principle and promising outlook for future device promotion and system optimization in the biomedical AI field.

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.

EESCN: A novel spiking neural network method for EEG-based emotion recognition

BACKGROUND AND OBJECTIVE

Although existing artificial neural networks have achieved good results in electroencephalograph (EEG) emotion recognition, further improvements are needed in terms of bio-interpretability and robustness. In this research, we aim to develop a highly efficient and high-performance method for emotion recognition based on EEG.

METHODS

We propose an Emo-EEGSpikeConvNet (EESCN), a novel emotion recognition method based on spiking neural network (SNN). It consists of a neuromorphic data generation module and a NeuroSpiking framework. The neuromorphic data generation module converts EEG data into 2D frame format as input to the NeuroSpiking framework, while the NeuroSpiking framework is used to extract spatio-temporal features of EEG for classification.

RESULTS

EESCN achieves high emotion recognition accuracies on DEAP and SEED-IV datasets, ranging from 94.56% to 94.81% on DEAP and a mean accuracy of 79.65% on SEED-IV. Compared to existing SNN methods, EESCN significantly improves EEG emotion recognition performance. In addition, it also has the advantages of faster running speed and less memory footprint.

CONCLUSIONS

EESCN has shown excellent performance and efficiency in EEG-based emotion recognition with potential for practical applications requiring portability and resource constraints.

Automated crystal system identification from electron diffraction patterns using multiview opinion fusion machine learning

A bottleneck in high-throughput nanomaterials discovery is the pace at which new materials can be structurally characterized. Although current machine learning (ML) methods show promise for the automated processing of electron diffraction patterns (DPs), they fail in high-throughput experiments where DPs are collected from crystals with random orientations. Inspired by the human decision-making process, a framework for automated crystal system classification from DPs with arbitrary orientations was developed. A convolutional neural network was trained using evidential deep learning, and the predictive uncertainties were quantified and leveraged to fuse multiview predictions. Using vector map representations of DPs, the framework achieves a testing accuracy of 0.94 in the examples considered, is robust to noise, and retains remarkable accuracy using experimental data. This work highlights the ability of ML to be used to accelerate experimental high-throughput materials data analytics.

Exploiting noise as a resource for computation and learning in spiking neural networks

Networks of spiking neurons underpin the extraordinary information-processing capabilities of the brain and have become pillar models in neuromorphic artificial intelligence. Despite extensive research on spiking neural networks (SNNs), most studies are established on deterministic models, overlooking the inherent non-deterministic, noisy nature of neural computations. This study introduces the noisy SNN (NSNN) and the noise-driven learning (NDL) rule by incorporating noisy neuronal dynamics to exploit the computational advantages of noisy neural processing. The NSNN provides a theoretical framework that yields scalable, flexible, and reliable computation and learning. We demonstrate that this framework leads to spiking neural models with competitive performance, improved robustness against challenging perturbations compared with deterministic SNNs, and better reproducing probabilistic computation in neural coding. Generally, this study offers a powerful and easy-to-use tool for machine learning, neuromorphic intelligence practitioners, and computational neuroscience researchers.

BIDL: a brain-inspired deep learning framework for spatiotemporal processing

Brain-inspired deep spiking neural network (DSNN) which emulates the function of the biological brain provides an effective approach for event-stream spatiotemporal perception (STP), especially for dynamic vision sensor (DVS) signals. However, there is a lack of generalized learning frameworks that can handle various spatiotemporal modalities beyond event-stream, such as video clips and 3D imaging data. To provide a unified design flow for generalized spatiotemporal processing (STP) and to investigate the capability of lightweight STP processing via brain-inspired neural dynamics, this study introduces a training platform called brain-inspired deep learning (BIDL). This framework constructs deep neural networks, which leverage neural dynamics for processing temporal information and ensures high-accuracy spatial processing via artificial neural network layers. We conducted experiments involving various types of data, including video information processing, DVS information processing, 3D medical imaging classification, and natural language processing. These experiments demonstrate the efficiency of the proposed method. Moreover, as a research framework for researchers in the fields of neuroscience and machine learning, BIDL facilitates the exploration of different neural models and enables global-local co-learning. For easily fitting to neuromorphic chips and GPUs, the framework incorporates several optimizations, including iteration representation, state-aware computational graph, and built-in neural functions. This study presents a user-friendly and efficient DSNN builder for lightweight STP applications and has the potential to drive future advancements in bio-inspired research.

A survey and perspective on neuromorphic continual learning systems

With the advent of low-power neuromorphic computing systems, new possibilities have emerged for deployment in various sectors, like healthcare and transport, that require intelligent autonomous applications. These applications require reliable low-power solutions for sequentially adapting to new relevant data without loss of learning. Neuromorphic systems are inherently inspired by biological neural networks that have the potential to offer an efficient solution toward the feat of continual learning. With increasing attention in this area, we present a first comprehensive review of state-of-the-art neuromorphic continual learning (NCL) paradigms. The significance of our study is multi-fold. We summarize the recent progress and propose a plausible roadmap for developing end-to-end NCL systems. We also attempt to identify the gap between research and the real-world deployment of NCL systems in multiple applications. We do so by assessing the recent contributions in neuromorphic continual learning at multiple levels-applications, algorithms, architectures, and hardware. We discuss the relevance of NCL systems and draw out application-specific requisites. We analyze the biological underpinnings that are used for acquiring high-level performance. At the hardware level, we assess the ability of the current neuromorphic platforms and emerging nano-device-based architectures to support these algorithms in the presence of several constraints. Further, we propose refinements to continual learning metrics for applying them to NCL systems. Finally, the review identifies gaps and possible solutions that are not yet focused upon for deploying application-specific NCL systems in real-life scenarios.

Flexible Floating-Gate Electric-Double-Layer Organic Transistor for Neuromorphic Computing

The key to the study of flexible neuromorphic computing is the excellent weight update characteristic of neuromorphic devices. Electric-double-layer transistors (EDLTs) include high transconductance, excellent stability of threshold voltage, linear weight updates, and repetitive ion-concentration-dependent switching properties. However, up to now, there is no report on a flexible EDLT that provides all the aforementioned performance characteristics. Here, a planar flexible floating-gate EDLT including an excellent linear/symmetric weight update, a large number (>800) of conductance states, repetitive switching endurance (>100 cycles), and low variation in weight update is reported. After 800 signal stimulations, it is found that the nonlinearity values of LTP are between 0.20 and 0.85, those of LTD fall between 0.66 and 1.55, the symmetricity values are between 120.7 and 639.8, and the dynamic range is between 150 and 352 nS. The study of 8 × 8 flexible floating-gate EDLT arrays shows that the average deviation and standard deviation between the experimental and theoretical values are 1.36 and 1.93, respectively, indicating that the conductance regulation in the array has a relatively small deviation. The different bending angles and the mechanical stability of the floating-gate EDLT are also studied, which exhibit the excellent bending properties. Furthermore, we studied the recognition of MNIST handwritten digit images by a three-layer perceptron artificial neural network with the experimental weight update, and the maximal recognition accuracy is up to 87.8%.

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.

The spike gating flow: A hierarchical structure-based spiking neural network for online gesture recognition

Action recognition is an exciting research avenue for artificial intelligence since it may be a game changer in emerging industrial fields such as robotic visions and automobiles. However, current deep learning (DL) faces major challenges for such applications because of the huge computational cost and inefficient learning. Hence, we developed a novel brain-inspired spiking neural network (SNN) based system titled spiking gating flow (SGF) for online action learning. The developed system consists of multiple SGF units which are assembled in a hierarchical manner. A single SGF unit contains three layers: a feature extraction layer, an event-driven layer, and a histogram-based training layer. To demonstrate the capability of the developed system, we employed a standard dynamic vision sensor (DVS) gesture classification as a benchmark. The results indicated that we can achieve 87.5% of accuracy which is comparable with DL, but at a smaller training/inference data number ratio of 1.5:1. Only a single training epoch is required during the learning process. Meanwhile, to the best of our knowledge, this is the highest accuracy among the non-backpropagation based SNNs. Finally, we conclude the few-shot learning (FSL) paradigm of the developed network: 1) a hierarchical structure-based network design involves prior human knowledge; 2) SNNs for content-based global dynamic feature detection.

Spike-Based Approximate Backpropagation Algorithm of Brain-Inspired Deep SNN for Sonar Target Classification

With the development of neuromorphic computing, more and more attention has been paid to a brain-inspired spiking neural network (SNN) because of its ultralow energy consumption and high-performance spatiotemporal information processing. Due to the discontinuity of the spiking neuronal activation function, it is still a difficult problem to train brain-inspired deep SNN directly, so SNN has not yet shown performance comparable to that of an artificial neural network. For this reason, the spike-based approximate backpropagation (SABP) algorithm and a general brain-inspired SNN framework are proposed in this paper. The combination of the two can be used for end-to-end direct training of brain-inspired deep SNN. Experiments show that compared with other spike-based methods of directly training SNN, the classification accuracy of this method is close to the best results on MNIST and CIFAR-10 datasets and achieves the best classification accuracy on sonar image target classification (SITC) of small sample datasets. Further analysis shows that compared with artificial neural networks, our brain-inspired SNN has great advantages in computational complexity and energy consumption in sonar target classification.

Enhancing spiking neural networks with hybrid top-down attention

As the representatives of brain-inspired models at the neuronal level, spiking neural networks (SNNs) have shown great promise in processing spatiotemporal information with intrinsic temporal dynamics. SNNs are expected to further improve their robustness and computing efficiency by introducing top-down attention at the architectural level, which is crucial for the human brain to support advanced intelligence. However, this attempt encounters difficulties in optimizing the attention in SNNs largely due to the lack of annotations. Here, we develop a hybrid network model with a top-down attention mechanism (HTDA) by incorporating an artificial neural network (ANN) to generate attention maps based on the features extracted by a feedforward SNN. The attention map is then used to modulate the encoding layer of the SNN so that it focuses on the most informative sensory input. To facilitate direct learning of attention maps and avoid labor-intensive annotations, we propose a general principle and a corresponding weakly-supervised objective, which promotes the HTDA model to utilize an integral and small subset of the input to give accurate predictions. On this basis, the ANN and the SNN can be jointly optimized by surrogate gradient descent in an end-to-end manner. We comprehensively evaluated the HTDA model on object recognition tasks, which demonstrates strong robustness to adversarial noise, high computing efficiency, and good interpretability. On the widely-adopted CIFAR-10, CIFAR-100, and MNIST benchmarks, the HTDA model reduces firing rates by up to 50% and improves adversarial robustness by up to 10% with comparable or better accuracy compared with the state-of-the-art SNNs. The HTDA model is also verified on dynamic neuromorphic datasets and achieves consistent improvements. This study provides a new way to boost the performance of SNNs by employing a hybrid top-down attention mechanism.

Post-silicon nano-electronic device and its application in brain-inspired chips

As information technology is moving toward the era of big data, the traditional Von-Neumann architecture shows limitations in performance. The field of computing has already struggled with the latency and bandwidth required to access memory (“the memory wall”) and energy dissipation (“the power wall”). These challenging issues, such as “the memory bottleneck,” call for significant research investments to develop a new architecture for the next generation of computing systems. Brain-inspired computing is a new computing architecture providing a method of high energy efficiency and high real-time performance for artificial intelligence computing. Brain-inspired neural network system is based on neuron and synapse. The memristive device has been proposed as an artificial synapse for creating neuromorphic computer applications. In this study, post-silicon nano-electronic device and its application in brain-inspired chips are surveyed. First, we introduce the development of neural networks and review the current typical brain-inspired chips, including brain-inspired chips dominated by analog circuit and brain-inspired chips of the full-digital circuit, leading to the design of brain-inspired chips based on post-silicon nano-electronic device. Then, through the analysis of N kinds of post-silicon nano-electronic devices, the research progress of constructing brain-inspired chips using post-silicon nano-electronic device is expounded. Lastly, the future of building brain-inspired chips based on post-silicon nano-electronic device has been prospected.

Lead federated neuromorphic learning for wireless edge artificial intelligence

In order to realize the full potential of wireless edge artificial intelligence (AI), very large and diverse datasets will often be required for energy-demanding model training on resource-constrained edge devices. This paper proposes a lead federated neuromorphic learning (LFNL) technique, which is a decentralized energy-efficient brain-inspired computing method based on spiking neural networks. The proposed technique will enable edge devices to exploit brain-like biophysiological structure to collaboratively train a global model while helping preserve privacy. Experimental results show that, under the situation of uneven dataset distribution among edge devices, LFNL achieves a comparable recognition accuracy to existing edge AI techniques, while substantially reducing data traffic by >3.5× and computational latency by >2.0×. Furthermore, LFNL significantly reduces energy consumption by >4.5× compared to standard federated learning with a slight accuracy loss up to 1.5%. Therefore, the proposed LFNL can facilitate the development of brain-inspired computing and edge AI.

Designing energy-efficient computing solution for the implementation of AI algorithms in edge devices remains a challenge. Yang et al. proposes a decentralized brain-inspired computing method enabling multiple edge devices to collaboratively train a global model without a fixed central coordinator.

A Synaptic Pruning-Based Spiking Neural Network for Hand-Written Digits Classification

A spiking neural network model inspired by synaptic pruning is developed and trained to extract features of hand-written digits. The network is composed of three spiking neural layers and one output neuron whose firing rate is used for classification. The model detects and collects the geometric features of the images from the Modified National Institute of Standards and Technology database (MNIST). In this work, a novel learning rule is developed to train the network to detect features of different digit classes. For this purpose, randomly initialized synaptic weights between the first and second layers are updated using average firing rates of pre- and postsynaptic neurons. Then, using a neuroscience-inspired mechanism named, “synaptic pruning” and its predefined threshold values, some of the synapses are deleted. Hence, these sparse matrices named, “information channels” are constructed so that they show highly specific patterns for each digit class as connection matrices between the first and second layers. The “information channels” are used in the test phase to assign a digit class to each test image. In addition, the role of feed-back inhibition as well as the connectivity rates of the second and third neural layers are studied. Similar to the abilities of the humans to learn from small training trials, the developed spiking neural network needs a very small dataset for training, compared to the conventional deep learning methods that have shown a very good performance on the MNIST dataset. This work introduces a new class of brain-inspired spiking neural networks to extract the features of complex data images.