Stochastic Spiking Neural Networks Research Articles

All Stochastic-Spiking Neural Network (AS-SNN): Noise Induced Spike Pulse Generator for Input and Output Neurons With Resistive Synaptic Array

All Stochastic-Spiking Neural Network (AS-SNN): Noise Induced Spike Pulse Generator for Input and Output Neurons With Resistive Synaptic Array

Neuromorphic computing with hybrid CNN–Stochastic Reservoir for time series WiFi based human activity recognition

Wi-Fi Channel State Information (CSI) based human activity recognition (HAR) which using channel disturbances caused by signal reflection is a novel way of environment sensing and motion recognition. The collected channels characteristics are heavily influenced by the environment, human activity patterns and subject’s weight and height. These signal variations reflected from body components are mainly affected by static multipath effects comprises random noise and behave differently in individuals, and thus an active field of research. To reach further for achieving automated real-time classification, lower computational cost and easy adaptability to hardware are necessary. In this work, a CSI-based HAR with hybrid framework, Convolutional Neural Network (CNN)-Stochastic Reservoir (SR) (CNN-SR) has been proposed, enabling a subject adaptable and more efficient hardware implementation with minimal computational complexity. A subcarrier correlation matrix is first computed and portrayed in image without preprocessing based on the reflection of the raw CSI signal induced by human activities at regular intervals, allowing visual observation of whole pattern changes. The time-based features are subsequently extracted through CNN and these feature arrays are then feed into SR which based on stochastic spiking neural network (SSNN) in simple cycle reservoir architecture for template matching. SR offers attractive power savings over typical von Neumann systems, by doing stochastic computations. The proposed method has also been demonstrated that is capable for HAR based on partially captured signals. The signal pattern of each segment can be observed in a single sight and then employed for person-to-person template recognition. This enables HAR with minimal computational complexity and solving the inter-person variability concerns. The results demonstrate that the proposed CNN-SR achieves impressive performance in recognizing human activities and surpasses existing models with an average accuracy of 93.49%.

Stochastic photonic spiking neuron for Bayesian inference with unsupervised learning.

Stochasticity is an inherent feature of biological neural activities. We propose a noise-injection scheme to implement a GHz-rate stochastic photonic spiking neuron (S-PSN). The firing-probability encoding is experimentally demonstrated and exploited for Bayesian inference with unsupervised learning. In a breast diagnosis task, the stochastic photonic spiking neural network (S-PSNN) can not only achieve a classification accuracy of 96.6%, but can also evaluate the diagnosis uncertainty with prediction entropies. As a result, the misdiagnosis rate is reduced by 80% compared to that of a conventional deterministic photonic spiking neural network (D-PSNN) for the same task. The GHz-rate S-PSN endows the neuromorphic photonics with high-speed Bayesian inference for reliable information processing in error-critical scenarios.

Color image perception based on stochastic spiking neural network

Our aim is to present an interpretable algorithm for enhancing low-illuminance color image based on the principle of stochastic resonance and the fundamental biophysical process of human brain perceiving object color. To this end, the phenomenon of stochastic resonance in a conductance-based integrate-and-fire neuronal network is first explored, with the effect of firing threshold, synaptic weight and the population size on the signal-to-noise ratio revealed, and the firing threshold is recognized as the key parameter for the resonance effects. And then, a color image enhancement algorithm, where the peak signal-to-noise ratio and the natural image quality evaluator are adopted as quantifying indexes, is developed by combining the stochastic spiking neuronal network and the involved biophysical process relating to visual perception. Note that the enhanced image is aperiodic, thus in order to optimize the performance of the algorithm, an illuminance distribution based threshold strategy is given by us for the first time. The numerical tests show that the algorithm has good enhancement performance and stability. We wish this algorithm could be applied to relevant signal processing fields such as military detection and medical image preprocessing.

SBSNN: Stochastic-Bits Enabled Binary Spiking Neural Network With On-Chip Learning for Energy Efficient Neuromorphic Computing at the Edge

In this work, we propose stochastic Binary Spiking Neural Network (sBSNN) composed of stochastic spiking neurons and binary synapses (stochastic only during training) that computes probabilistically with one-bit precision for power-efficient and memory-compressed neuromorphic computing. We present an energy-efficient implementation of the proposed sBSNN using ‘stochastic bit’ as the core computational primitive to realize the stochastic neurons and synapses, which are fabricated in 90nm CMOS process, to achieve efficient on-chip training and inference for image recognition tasks. The measured data shows that the ‘stochastic bit’ can be programmed to mimic spiking neurons, and stochastic Spike Timing Dependent Plasticity (or sSTDP) rule for training the binary synaptic weights without expensive random number generators. Our results indicate that the proposed sBSNN realization offers possibility of up to $32\times $ neuronal and synaptic memory compression compared to full precision (32-bit) SNN and energy efficiency of 89.49 TOPS/Watt for two-layer fully-connected SNN.

Subthreshold Spintronic Stochastic Spiking Neural Networks With Probabilistic Hebbian Plasticity and Homeostasis

The neural sampling core (NSC) proposed herein offers a spintronic device-based circuit and learning mechanism utilizing imprecise and stochastic components, similar to biological brains, to realize ultralow-power neuromorphic computations at subthreshold voltages. Leveraging principles from neural sampling, a biologically plausible theory from computational neuroscience, a spintronic stochastic spiking neuron with digital Postsynaptic potentials is proposed in conjunction with low-precision spintronic synapses utilizing a new event-driven Probabilistic Hebbian Plasticity Rule, and a novel homeostasis mechanism that balances neural activity across multiple timescales and process variation effects. The primary computational operation, the summation of presynaptic potentials weighted by their corresponding synaptic efficacy and the neuron’s homeostatic parameters, is performed in a parallel analog fashion using noisy and imprecise subthreshold components. It is demonstrated herein that the NSC is capable of learning orientation selectivity, much like the simple cells found in the visual cortex, in an unsupervised fashion at 311 nW per neuron and 1.9–7.7 nW per active synapse using a 200-mV supply voltage.

ReStoCNet: Residual Stochastic Binary Convolutional Spiking Neural Network for Memory-Efficient Neuromorphic Computing.

In this work, we propose ReStoCNet, a residual stochastic multilayer convolutional Spiking Neural Network (SNN) composed of binary kernels, to reduce the synaptic memory footprint and enhance the computational efficiency of SNNs for complex pattern recognition tasks. ReStoCNet consists of an input layer followed by stacked convolutional layers for hierarchical input feature extraction, pooling layers for dimensionality reduction, and fully-connected layer for inference. In addition, we introduce residual connections between the stacked convolutional layers to improve the hierarchical feature learning capability of deep SNNs. We propose Spike Timing Dependent Plasticity (STDP) based probabilistic learning algorithm, referred to as Hybrid-STDP (HB-STDP), incorporating Hebbian and anti-Hebbian learning mechanisms, to train the binary kernels forming ReStoCNet in a layer-wise unsupervised manner. We demonstrate the efficacy of ReStoCNet and the presented HB-STDP based unsupervised training methodology on the MNIST and CIFAR-10 datasets. We show that residual connections enable the deeper convolutional layers to self-learn useful high-level input features and mitigate the accuracy loss observed in deep SNNs devoid of residual connections. The proposed ReStoCNet offers >20 × kernel memory compression compared to full-precision (32-bit) SNN while yielding high enough classification accuracy on the chosen pattern recognition tasks.

An All-Memristor Deep Spiking Neural Computing System: A Step Toward Realizing the Low-Power Stochastic Brain

Deep analog artificial neural networks (ANNs) perform complex classification problems with remarkably high accuracy. However, they rely on humongous amount of power to perform the calculations, veiling the accuracy benefits. The biological brain, on the other hand, is significantly more powerful than such networks and consumes orders of magnitude less power, indicating us about some conceptual mismatch. Given that the biological neurons communicate using energy efficient trains of spikes, and the behavior is nondeterministic, incorporating these effects in deep artificial neural networks may drive us few steps toward a more realistic neuron. In this paper, we propose how the inherent stochasticity of nanoscale resistive devices can be harnessed to emulate the functionality of a spiking neuron that can be incorporated in deep stochastic spiking neural networks (SNN). At the algorithmic level, we propose how the training can be modified to convert an ANN to an SNN while supporting the stochastic activation function offered by these devices. We devise circuit architectures to incorporate stochastic memristive neurons along with memristive crossbars, which perform the functionality of the synaptic weights. We tested the proposed all-memristor deep stochastic SNN for image classification and observed only about 1% degradation in accuracy with the ANN baseline after incorporating the circuit and device related nonidealities. We witnessed that the network is robust to certain variations and consumes ~6.4 × less energy than its complementary metal oxide semiconductor (CMOS) counterpart.

Using Stochastic Spiking Neural Networks on SpiNNaker to Solve Constraint Satisfaction Problems.

Constraint satisfaction problems (CSP) are at the core of numerous scientific and technological applications. However, CSPs belong to the NP-complete complexity class, for which the existence (or not) of efficient algorithms remains a major unsolved question in computational complexity theory. In the face of this fundamental difficulty heuristics and approximation methods are used to approach instances of NP (e.g., decision and hard optimization problems). The human brain efficiently handles CSPs both in perception and behavior using spiking neural networks (SNNs), and recent studies have demonstrated that the noise embedded within an SNN can be used as a computational resource to solve CSPs. Here, we provide a software framework for the implementation of such noisy neural solvers on the SpiNNaker massively parallel neuromorphic hardware, further demonstrating their potential to implement a stochastic search that solves instances of P and NP problems expressed as CSPs. This facilitates the exploration of new optimization strategies and the understanding of the computational abilities of SNNs. We demonstrate the basic principles of the framework by solving difficult instances of the Sudoku puzzle and of the map color problem, and explore its application to spin glasses. The solver works as a stochastic dynamical system, which is attracted by the configuration that solves the CSP. The noise allows an optimal exploration of the space of configurations, looking for the satisfiability of all the constraints; if applied discontinuously, it can also force the system to leap to a new random configuration effectively causing a restart.

Stochastic Spiking Neural Networks Enabled by Magnetic Tunnel Junctions: From Nontelegraphic to Telegraphic Switching Regimes

Stochastic spiking neural networks based on nanoelectronic spin devices can be a possible pathway to achieving "brainlike" compact and energy-effcient cognitive intelligence. The computational model attempt to exploit the intrinsic device stochasticity of nanoelectronic synaptic or neural components to perform learning or inference. However, there has been limited analysis on the scaling effect of stochastic spin devices and its impact on the operation of such stochastic networks at the system level. This work attempts to explore the design space and analyze the performance of nanomagnet-based stochastic neuromorphic computing architectures for magnets with different barrier heights. We illustrate how the underlying network architecture must be modified to account for the random telegraphic switching behavior displayed by magnets with low barrier heights as they are scaled into the superparamagnetic regime. We perform a device-to-system-level analysis on a deep neural-network architecture for a digit-recognition problem on the MNIST data set.

Exploring the limits of learning: Segregation of information integration and response selection is required for learning a serial reversal task.

Animals are proposed to learn the latent rules governing their environment in order to maximize their chances of survival. However, rules may change without notice, forcing animals to keep a memory of which one is currently at work. Rule switching can lead to situations in which the same stimulus/response pairing is positively and negatively rewarded in the long run, depending on variables that are not accessible to the animal. This fact raises questions on how neural systems are capable of reinforcement learning in environments where the reinforcement is inconsistent. Here we address this issue by asking about which aspects of connectivity, neural excitability and synaptic plasticity are key for a very general, stochastic spiking neural network model to solve a task in which rules change without being cued, taking the serial reversal task (SRT) as paradigm. Contrary to what could be expected, we found strong limitations for biologically plausible networks to solve the SRT. Especially, we proved that no network of neurons can learn a SRT if it is a single neural population that integrates stimuli information and at the same time is responsible of choosing the behavioural response. This limitation is independent of the number of neurons, neuronal dynamics or plasticity rules, and arises from the fact that plasticity is locally computed at each synapse, and that synaptic changes and neuronal activity are mutually dependent processes. We propose and characterize a spiking neural network model that solves the SRT, which relies on separating the functions of stimuli integration and response selection. The model suggests that experimental efforts to understand neural function should focus on the characterization of neural circuits according to their connectivity, neural dynamics, and the degree of modulation of synaptic plasticity with reward.

Dynamical neuronal gains produce self-organized criticality in stochastic spiking neural networks.

Dynamical neuronal gains produce self-organized criticality in stochastic spiking neural networks.

Studying the role of synchronized and chaotic spiking neural ensembles in neural information processing.

The brain is characterized by performing many diverse processing tasks ranging from elaborate processes such as pattern recognition, memory or decision making to more simple functionalities such as linear filtering in image processing. Understanding the mechanisms by which the brain is able to produce such a different range of cortical operations remains a fundamental problem in neuroscience. Here we show a study about which processes are related to chaotic and synchronized states based on the study of in-silico implementation of Stochastic Spiking Neural Networks (SSNN). The measurements obtained reveal that chaotic neural ensembles are excellent transmission and convolution systems since mutual information between signals is minimized. At the same time, synchronized cells (that can be understood as ordered states of the brain) can be associated to more complex nonlinear computations. In this sense, we experimentally show that complex and quick pattern recognition processes arise when both synchronized and chaotic states are mixed. These measurements are in accordance with in vivo observations related to the role of neural synchrony in pattern recognition and to the speed of the real biological process. We also suggest that the high-level adaptive mechanisms of the brain that are the Hebbian and non-Hebbian learning rules can be understood as processes devoted to generate the appropriate clustering of both synchronized and chaotic ensembles. The measurements obtained from the hardware implementation of different types of neural systems suggest that the brain processing can be governed by the superposition of these two complementary states with complementary functionalities (nonlinear processing for synchronized states and information convolution and parallelization for chaotic).

A Markovian event-based framework for stochastic spiking neural networks

In spiking neural networks, the information is conveyed by the spike times, that depend on the intrinsic dynamics of each neuron, the input they receive and on the connections between neurons. In this article we study the Markovian nature of the sequence of spike times in stochastic neural networks, and in particular the ability to deduce from a spike train the next spike time, and therefore produce a description of the network activity only based on the spike times regardless of the membrane potential process. To study this question in a rigorous manner, we introduce and study an event-based description of networks of noisy integrate-and-fire neurons, i.e. that is based on the computation of the spike times. We show that the firing times of the neurons in the networks constitute a Markov chain, whose transition probability is related to the probability distribution of the interspike interval of the neurons in the network. In the cases where the Markovian model can be developed, the transition probability is explicitly derived in such classical cases of neural networks as the linear integrate-and-fire neuron models with excitatory and inhibitory interactions, for different types of synapses, possibly featuring noisy synaptic integration, transmission delays and absolute and relative refractory period. This covers most of the cases that have been investigated in the event-based description of spiking deterministic neural networks.