The HTM Spatial Pooler-A Neocortical Algorithm for Online Sparse Distributed Coding

NeoSLAM: Long-Term SLAM Using Computational Models of the Brain

Simultaneous Localization and Mapping (SLAM) is a fundamental problem in the field of robotics, enabling autonomous robots to navigate and create maps of unknown environments. Nevertheless, the SLAM methods that use cameras face problems in maintaining accurate localization over extended periods across various challenging conditions and scenarios. Following advances in neuroscience, we propose NeoSLAM, a novel long-term visual SLAM, which uses computational models of the brain to deal with this problem. Inspired by the human neocortex, NeoSLAM is based on a hierarchical temporal memory model that has the potential to identify temporal sequences of spatial patterns using sparse distributed representations. Being known to have a high representational capacity and high tolerance to noise, sparse distributed representations have several properties, enabling the development of a novel neuroscience-based loop-closure detector that allows for real-time performance, especially in resource-constrained robotic systems. The proposed method has been thoroughly evaluated in terms of environmental complexity by using a wheeled robot deployed in the field and demonstrated that the accuracy of loop-closure detection was improved compared with the traditional RatSLAM system.

Discovering anomalies in big data: a review focused on the application of metaheuristics and machine learning techniques

With the increase in available data from computer systems and their security threats, interest in anomaly detection has increased as well in recent years. The need to diagnose faults and cyberattacks has also focused scientific research on the automated classification of outliers in big data, as manual labeling is difficult in practice due to their huge volumes. The results obtained from data analysis can be used to generate alarms that anticipate anomalies and thus prevent system failures and attacks. Therefore, anomaly detection has the purpose of reducing maintenance costs as well as making decisions based on reports. During the last decade, the approaches proposed in the literature to classify unknown anomalies in log analysis, process analysis, and time series have been mainly based on machine learning and deep learning techniques. In this study, we provide an overview of current state-of-the-art methodologies, highlighting their advantages and disadvantages and the new challenges. In particular, we will see that there is no absolute best method, i.e., for any given dataset a different method may achieve the best result. Finally, we describe how the use of metaheuristics within machine learning algorithms makes it possible to have more robust and efficient tools.

Perfect synchronization in complex networks with higher-order interactions

Achieving perfect synchronization in a complex network, specially in the presence of higher-order interactions (HOIs) at a targeted point in the parameter space, is an interesting, yet challenging task. Here we present a theoretical framework to achieve the same under the paradigm of the Sakaguchi-Kuramoto (SK) model. We analytically derive a frequency set to achieve perfect synchrony at some desired point in a complex network of SK oscillators with higher-order interactions. Considering the SK model with HOIs on top of the scale-free, random, and small world networks, we perform extensive numerical simulations to verify the proposed theory. Numerical simulations show that the analytically derived frequency set not only provides stable perfect synchronization in the network at a desired point but also proves to be very effective in achieving a high level of synchronization around it compared to the other choices of frequency sets. The stability and the robustness of the perfect synchronization state of the system are determined using the low-dimensional reduction of the network and by introducing a Gaussian noise around the derived frequency set, respectively.

Information-theoretic analysis of Hierarchical Temporal Memory-Spatial Pooler algorithm with a new upper bound for the standard information bottleneck method

Hierarchical Temporal Memory (HTM) is an unsupervised algorithm in machine learning. It models several fundamental neocortical computational principles. Spatial Pooler (SP) is one of the main components of the HTM, which continuously encodes streams of binary input from various layers and regions into sparse distributed representations. In this paper, the goal is to evaluate the sparsification in the SP algorithm from the perspective of information theory by the information bottleneck (IB), Cramer-Rao lower bound, and Fisher information matrix. This paper makes two main contributions. First, we introduce a new upper bound for the standard information bottleneck relation, which we refer to as modified-IB in this paper. This measure is used to evaluate the performance of the SP algorithm in different sparsity levels and various amounts of noise. The MNIST, Fashion-MNIST and NYC-Taxi datasets were fed to the SP algorithm separately. The SP algorithm with learning was found to be resistant to noise. Adding up to 40% noise to the input resulted in no discernible change in the output. Using the probabilistic mapping method and Hidden Markov Model, the sparse SP output representation was reconstructed in the input space. In the modified-IB relation, it is numerically calculated that a lower noise level and a higher sparsity level in the SP algorithm lead to a more effective reconstruction and SP with 2% sparsity produces the best results. Our second contribution is to prove mathematically that more sparsity leads to better performance of the SP algorithm. The data distribution was considered the Cauchy distribution, and the Cramer-Rao lower bound was analyzed to estimate SP's output at different sparsity levels.

GridHTM: Grid-Based Hierarchical Temporal Memory for Anomaly Detection in Videos

The interest in video anomaly detection systems that can detect different types of anomalies, such as violent behaviours in surveillance videos, has gained traction in recent years. The current approaches employ deep learning to perform anomaly detection in videos, but this approach has multiple problems. For example, deep learning in general has issues with noise, concept drift, explainability, and training data volumes. Additionally, anomaly detection in itself is a complex task and faces challenges such as unknownness, heterogeneity, and class imbalance. Anomaly detection using deep learning is therefore mainly constrained to generative models such as generative adversarial networks and autoencoders due to their unsupervised nature; however, even they suffer from general deep learning issues and are hard to properly train. In this paper, we explore the capabilities of the Hierarchical Temporal Memory (HTM) algorithm to perform anomaly detection in videos, as it has favorable properties such as noise tolerance and online learning which combats concept drift. We introduce a novel version of HTM, named GridHTM, which is a grid-based HTM architecture specifically for anomaly detection in complex videos such as surveillance footage. We have tested GridHTM using the VIRAT video surveillance dataset, and the subsequent evaluation results and online learning capabilities prove the great potential of using our system for real-time unsupervised anomaly detection in complex videos.

Study on the diversity of mental states and neuroplasticity of the brain during human-machine interaction

Introduction

With the increasing demand for human-machine collaboration systems, more and more attention has been paid to the influence of human factors on the performance and security of the entire system. Especially in high-risk, high-precision, and difficult special tasks (such as space station maintenance tasks, anti-terrorist EOD tasks, surgical robot teleoperation tasks, etc.), there are higher requirements for the operator's perception and cognitive level. However, as the human brain is a complex and open giant system, the perception ability and cognitive level of the human are dynamically variable, so that it will seriously affect the performance and security of the whole system.

Methods

The method proposed in this paper innovatively explained this phenomenon from two dimensions of brain space and time and attributed the dynamic changes of perception, cognitive level, and operational skills to the mental state diversity and the brain neuroplasticity. In terms of the mental state diversity, the mental states evoked paradigm and the functional brain network analysis method during work were proposed. In terms of neuroplasticity, the cognitive training intervention paradigm and the functional brain network analysis method were proposed. Twenty-six subjects participated in the mental state evoked experiment and the cognitive training intervention experiment.

Results

The results showed that (1) the mental state of the subjects during work had the characteristics of dynamic change, and due to the influence of stimulus conditions and task patterns, the mental state showed diversity. There were significant differences between functional brain networks in different mental states, the information processing efficiency and the mechanism of brain area response had changed significantly. (2) The small-world attributes of the functional brain network of the subjects before and after the cognitive training experiment were significantly different. The brain had adjusted the distribution of information flow and resources, reducing costs and increasing efficiency as a whole. It was demonstrated that the global topology of the cortical connectivity network was reconfigured and neuroplasticity was altered through cognitive training intervention.

Discussion

In summary, this paper revealed that mental state and neuroplasticity could change the information processing efficiency and the response mechanism of brain area, thus causing the change of perception, cognitive level and operational skills, which provided a theoretical basis for studying the relationship between neural information processing and behavior.

Computational Modeling of Structural Synaptic Plasticity in Echo State Networks

Most existing studies on computational modeling of neural plasticity have focused on synaptic plasticity. However, regulation of the internal weights in the reservoir based on synaptic plasticity often results in unstable learning dynamics. In this article, a structural synaptic plasticity learning rule is proposed to train the weights and add or remove neurons within the reservoir, which is shown to be able to alleviate the instability of the synaptic plasticity, and to contribute to increase the memory capacity of the network as well. Our experimental results also reveal that a few stronger connections may last for a longer period of time in a constantly changing network structure, and are relatively resistant to decay or disruptions in the learning process. These results are consistent with the evidence observed in biological systems. Finally, we show that an echo state network (ESN) using the proposed structural plasticity rule outperforms an ESN using synaptic plasticity and three state-of-the-art ESNs on four benchmark tasks.

Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments

A key challenge for AI is to build embodied systems that operate in dynamically changing environments. Such systems must adapt to changing task contexts and learn continuously. Although standard deep learning systems achieve state of the art results on static benchmarks, they often struggle in dynamic scenarios. In these settings, error signals from multiple contexts can interfere with one another, ultimately leading to a phenomenon known as catastrophic forgetting. In this article we investigate biologically inspired architectures as solutions to these problems. Specifically, we show that the biophysical properties of dendrites and local inhibitory systems enable networks to dynamically restrict and route information in a context-specific manner. Our key contributions are as follows: first, we propose a novel artificial neural network architecture that incorporates active dendrites and sparse representations into the standard deep learning framework. Next, we study the performance of this architecture on two separate benchmarks requiring task-based adaptation: Meta-World, a multi-task reinforcement learning environment where a robotic agent must learn to solve a variety of manipulation tasks simultaneously; and a continual learning benchmark in which the model's prediction task changes throughout training. Analysis on both benchmarks demonstrates the emergence of overlapping but distinct and sparse subnetworks, allowing the system to fluidly learn multiple tasks with minimal forgetting. Our neural implementation marks the first time a single architecture has achieved competitive results in both multi-task and continual learning settings. Our research sheds light on how biological properties of neurons can inform deep learning systems to address dynamic scenarios that are typically impossible for traditional ANNs to solve.

The neural coding framework for learning generative models

Neural generative models can be used to learn complex probability distributions from data, to sample from them, and to produce probability density estimates. We propose a computational framework for developing neural generative models inspired by the theory of predictive processing in the brain. According to predictive processing theory, the neurons in the brain form a hierarchy in which neurons in one level form expectations about sensory inputs from another level. These neurons update their local models based on differences between their expectations and the observed signals. In a similar way, artificial neurons in our generative models predict what neighboring neurons will do, and adjust their parameters based on how well the predictions matched reality. In this work, we show that the neural generative models learned within our framework perform well in practice across several benchmark datasets and metrics and either remain competitive with or significantly outperform other generative models with similar functionality (such as the variational auto-encoder).

Hierarchical intrinsically motivated agent planning behavior with dreaming in grid environments

Biologically plausible models of learning may provide a crucial insight for building autonomous intelligent agents capable of performing a wide range of tasks. In this work, we propose a hierarchical model of an agent operating in an unfamiliar environment driven by a reinforcement signal. We use temporal memory to learn sparse distributed representation of state–actions and the basal ganglia model to learn effective action policy on different levels of abstraction. The learned model of the environment is utilized to generate an intrinsic motivation signal, which drives the agent in the absence of the extrinsic signal, and through acting in imagination, which we call dreaming. We demonstrate that the proposed architecture enables an agent to effectively reach goals in grid environments.

Orientation Invariant Sensorimotor Object Recognition Using Cortical Grid Cells

Grid cells enable efficient modeling of locations and movement through path integration. Recent work suggests that the brain might use similar mechanisms to learn the structure of objects and environments through sensorimotor processing. This work is extended in our network to support sensor orientations relative to learned allocentric object representations. The proposed mechanism enables object representations to be learned through sensorimotor sequences, and inference of these learned object representations from novel sensorimotor sequences produced by rotated objects through path integration. The model proposes that orientation-selective cells are present in each column in the neocortex, and provides a biologically plausible implementation that echoes experimental measurements and fits in with theoretical predictions of previous studies.

A thousand brains: toward biologically constrained AI

This paper reviews the state of artificial intelligence (AI) and the quest to create general AI with human-like cognitive capabilities. Although existing AI methods have produced powerful applications that outperform humans in specific bounded domains, these techniques have fundamental limitations that hinder the creation of general intelligent systems. In parallel, over the last few decades, an explosion of experimental techniques in neuroscience has significantly increased our understanding of the human brain. This review argues that improvements in current AI using mathematical or logical techniques are unlikely to lead to general AI. Instead, the AI community should incorporate neuroscience discoveries about the neocortex, the human brain’s center of intelligence. The article explains the limitations of current AI techniques. It then focuses on the biologically constrained Thousand Brains Theory describing the neocortex’s computational principles. Future AI systems can incorporate these principles to overcome the stated limitations of current systems. Finally, the article concludes that AI researchers and neuroscientists should work together on specified topics to achieve biologically constrained AI with human-like capabilities.

Anomalous Behavior Detection Framework Using HTM-Based Semantic Folding Technique

Upon the working principles of the human neocortex, the Hierarchical Temporal Memory model has been developed which is a proposed theoretical framework for sequence learning. Both categorical and numerical types of data are handled by HTM. Semantic Folding Theory (SFT) is based on HTM to represent a data stream for processing in the form of sparse distributed representation (SDR). For natural language perception and production, SFT delivers a solid structural background for semantic evidence description to the fundamentals of the semantic foundation during the phase of language learning. Anomalies are the patterns from data streams that do not follow the expected behavior. Any stream of data patterns could have a number of anomaly types. In a data stream, a single pattern or combination of closely related patterns that diverges and deviates from standard, normal, or expected is called a static (spatial) anomaly. A temporal anomaly is a set of unexpected changes between patterns. When a change first appears, this is recorded as an anomaly. If this change looks a number of times, then it is set to a “new normal” and terminated as an anomaly. An HTM system detects the anomaly, and due to continuous learning nature, it quickly learns when they become the new normal. A robust anomalous behavior detection framework using HTM-based SFT for improving decision-making (SDR-ABDF/P2) is a proposed framework or model in this research. The researcher claims that the proposed model would be able to learn the order of several variables continuously in temporal sequences by using an unsupervised learning rule.

Exploiting defective RRAM array as synapses of HTM spatial pooler with boost-factor adjustment scheme for defect-tolerant neuromorphic systems

A crossbar array architecture employing resistive switching memory (RRAM) as a synaptic element accelerates vector-matrix multiplication in a parallel fashion, enabling energy-efficient pattern recognition. To implement the function of the synapse in the RRAM, multilevel resistance states are required. More importantly, a large on/off ratio of the RRAM should be preferentially obtained to ensure a reasonable margin between each state taking into account the inevitable variability caused by the inherent switching mechanism. The on/off ratio is basically adjusted in two ways by modulating measurement conditions such as compliance current or voltage pulses modulation. The latter technique is not only more suitable for practical systems, but also can achieve multiple states in low current range. However, at the expense of applying a high negative voltage aimed at enlarging the on/off ratio, a breakdown of the RRAM occurs unexpectedly. This stuck-at-short fault of the RRAM adversely affects the recognition process based on reading and judging each column current changed by the multiplication of the input voltage and resistance of the RRAM in the array, degrading the accuracy. To address this challenge, we introduce a boost-factor adjustment technique as a fault-tolerant scheme based on simple circuitry that eliminates the additional process to identify specific locations of the failed RRAMs in the array. Spectre circuit simulation is performed to verify the effect of the scheme on Modified National Institute of Standards and Technology dataset using convolutional neural networks in non-ideal crossbar arrays, where experimentally observed imperfective RRAMs are configured. Our results show that the recognition accuracy can be maintained similar to the ideal case because the interruption of the failure is suppressed by the scheme.

Online Intrusion Scenario Discovery and Prediction Based on Hierarchical Temporal Memory (HTM)

With the development of intrusion detection, a number of the intelligence algorithms (e.g., artificial neural networks) are introduced to enhance the performance of the intrusion detection systems. However, many intelligence algorithms should be trained before being used, and retrained regularly, which is not applicable for continuous online learning and analyzing. In this paper, a new online intrusion scenario discovery framework is proposed and the intelligence algorithm HTM (Hierarchical Temporal Memory) is employed to improve the performance of the online learning ability of the system. The proposed framework can discover and model intrusion scenarios, and the constructed model keeps evolving with the variance of the data. Additionally, a series of data preprocessing methods are introduced to enhance its adaptability to the noisy and twisted data. The experimental results show that the framework is effective in intrusion scenario discovery, and the discovered scenario is more concise and accurate than our previous work.

Self-Structured Cortical Learning Algorithm by Dynamically Adjusting Columns and Cells

The cortical learning algorithm (CLA) is a type of time-series data prediction algorithm based on the human neocortex. CLA uses multiple columns to represent an input data value at a timestep, and each column has multiple cells to represent the time-series context of the input data. In the conventional CLA, the numbers of columns and cells are user-defined parameters. These parameters depend on the input data, which can be unknown before learning. To avoid the necessity for setting these parameters beforehand, in this work, we propose a self-structured CLA that dynamically adjusts the numbers of columns and cells according to the input data. The experimental results using the time-series test inputs of a sine wave, combined sine wave, and logistic map data demonstrate that the proposed self-structured algorithm can dynamically adjust the numbers of columns and cells depending on the input data. Moreover, the prediction accuracy is higher than those of the conventional long short-term memory and CLAs with various fixed numbers of columns and cells. Furthermore, the experimental results on a multistep prediction of real-world power consumption show that the proposed self-structured CLA achieves a higher prediction accuracy than the conventional long short-term memory.

Gait Recognition and Understanding Based on Hierarchical Temporal Memory Using 3D Gait Semantic Folding

Gait recognition and understanding systems have shown a wide-ranging application prospect. However, their use of unstructured data from image and video has affected their performance, e.g., they are easily influenced by multi-views, occlusion, clothes, and object carrying conditions. This paper addresses these problems using a realistic 3-dimensional (3D) human structural data and sequential pattern learning framework with top-down attention modulating mechanism based on Hierarchical Temporal Memory (HTM). First, an accurate 2-dimensional (2D) to 3D human body pose and shape semantic parameters estimation method is proposed, which exploits the advantages of an instance-level body parsing model and a virtual dressing method. Second, by using gait semantic folding, the estimated body parameters are encoded using a sparse 2D matrix to construct the structural gait semantic image. In order to achieve time-based gait recognition, an HTM Network is constructed to obtain the sequence-level gait sparse distribution representations (SL-GSDRs). A top-down attention mechanism is introduced to deal with various conditions including multi-views by refining the SL-GSDRs, according to prior knowledge. The proposed gait learning model not only aids gait recognition tasks to overcome the difficulties in real application scenarios but also provides the structured gait semantic images for visual cognition. Experimental analyses on CMU MoBo, CASIA B, TUM-IITKGP, and KY4D datasets show a significant performance gain in terms of accuracy and robustness.

Hybrid Circuit of Memristor and Complementary Metal-Oxide-Semiconductor for Defect-Tolerant Spatial Pooling with Boost-Factor Adjustment

Hierarchical Temporal Memory (HTM) has been known as a software framework to model the brain's neocortical operation. However, mimicking the brain's neocortical operation by not software but hardware is more desirable, because the hardware can not only describe the neocortical operation, but can also employ the brain's architectural advantages. To develop a hybrid circuit of memristor and Complementary Metal-Oxide-Semiconductor (CMOS) for realizing HTM's spatial pooler (SP) by hardware, memristor defects such as stuck-at-faults and variations should be considered. For solving the defect problem, we first show that the boost-factor adjustment can make HTM's SP defect-tolerant, because the false activation of defective columns are suppressed. Second, we propose a memristor-CMOS hybrid circuit with the boost-factor adjustment to realize this defect-tolerant SP by hardware. The proposed circuit does not rely on the conventional defect-aware mapping scheme, which cannot avoid the false activation of defective columns. For the Modified subset of National Institute of Standards and Technology (MNIST) vectors, the boost-factor adjusted crossbar with defects = 10% shows a rate loss of only ~0.6%, compared to the ideal crossbar with defects = 0%. On the contrary, the defect-aware mapping without the boost-factor adjustment demonstrates a significant rate loss of ~21.0%. The energy overhead of the boost-factor adjustment is only ~0.05% of the programming energy of memristor synapse crossbar.

Memristor-CMOS Hybrid Circuit for Temporal-Pooling of Sensory and Hippocampal Responses of Cortical Neurons

As a software framework, Hierarchical Temporal Memory (HTM) has been developed to perform the brain’s neocortical functions, such as spatial and temporal pooling. However, it should be realized with hardware not software not only to mimic the neocortical function but also to exploit its architectural benefit. To do so, we propose a new memristor-CMOS (Complementary Metal-Oxide-Semiconductor) hybrid circuit of temporal-pooling here, which is composed of the input-layer and output-layer neurons mimicking the neocortex. In the hybrid circuit, the input-layer neurons have the proximal and basal/distal dendrites to combine sensory information with the temporal/location information from the brain’s hippocampus. Using the same crossbar architecture, the output-layer neurons can perform a prediction by integrating the temporal information on the basal/distal dendrites. For training the proposed circuit, we used only simple Hebbian learning, not the complicated backpropagation algorithm. Due to the simple hardware of Hebbian learning, the proposed hybrid circuit can be very suitable to online learning. The proposed memristor-CMOS hybrid circuit has been verified by the circuit simulation using the real memristor model. The proposed circuit has been verified to predict both the ordinal and out-of-order sequences. In addition, the proposed circuit has been tested with the external noise and memristance variation.

A neural data structure for novelty detection

Novelty detection is a fundamental biological problem that organisms must solve to determine whether a given stimulus departs from those previously experienced. In computer science, this problem is solved efficiently using a data structure called a Bloom filter. We found that the fruit fly olfactory circuit evolved a variant of a Bloom filter to assess the novelty of odors. Compared with a traditional Bloom filter, the fly adjusts novelty responses based on two additional features: the similarity of an odor to previously experienced odors and the time elapsed since the odor was last experienced. We elaborate and validate a framework to predict novelty responses of fruit flies to given pairs of odors. We also translate insights from the fly circuit to develop a class of distance- and time-sensitive Bloom filters that outperform prior filters when evaluated on several biological and computational datasets. Overall, our work illuminates the algorithmic basis of an important neurobiological problem and offers strategies for novelty detection in computational systems.