Unsupervised Feature Learning With Winner-Takes-All Based STDP

An unsupervised STDP-based spiking neural network inspired by biologically plausible learning rules and connections

The backpropagation algorithm has promoted the rapid development of deep learning, but it relies on a large amount of labeled data and still has a large gap with how humans learn. The human brain can quickly learn various conceptual knowledge in a self-organized and unsupervised manner, accomplished through coordinating various learning rules and structures in the human brain. Spike-timing-dependent plasticity (STDP) is a general learning rule in the brain, but spiking neural networks (SNNs) trained with STDP alone is inefficient and perform poorly. In this paper, taking inspiration from short-term synaptic plasticity, we design an adaptive synaptic filter and introduce the adaptive spiking threshold as the neuron plasticity to enrich the representation ability of SNNs. We also introduce an adaptive lateral inhibitory connection to adjust the spikes balance dynamically to help the network learn richer features. To speed up and stabilize the training of unsupervised spiking neural networks, we design a samples temporal batch STDP (STB-STDP), which updates weights based on multiple samples and moments. By integrating the above three adaptive mechanisms and STB-STDP, our model greatly accelerates the training of unsupervised spiking neural networks and improves the performance of unsupervised SNNs on complex tasks. Our model achieves the current state-of-the-art performance of unsupervised STDP-based SNNs in the MNIST and FashionMNIST datasets. Further, we tested on the more complex CIFAR10 dataset, and the results fully illustrate the superiority of our algorithm. Our model is also the first work to apply unsupervised STDP-based SNNs to CIFAR10. At the same time, in the small-sample learning scenario, it will far exceed the supervised ANN using the same structure.

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.

Selective area doping for Mott neuromorphic electronics

The cointegration of artificial neuronal and synaptic devices with homotypic materials and structures can greatly simplify the fabrication of neuromorphic hardware. We demonstrate experimental realization of vanadium dioxide (VO₂) artificial neurons and synapses on the same substrate through selective area carrier doping. By locally configuring pairs of catalytic and inert electrodes that enable nanoscale control over carrier density, volatility or nonvolatility can be appropriately assigned to each two-terminal Mott memory device per lithographic design, and both neuron- and synapse-like devices are successfully integrated on a single chip. Feedforward excitation and inhibition neural motifs are demonstrated at hardware level, followed by simulation of network-level handwritten digit and fashion product recognition tasks with experimental characteristics. Spatially selective electron doping opens up previously unidentified avenues for integration of emerging correlated semiconductors in electronic device technologies.

LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing

Spiking neural networks (SNNs) based on the leaky integrate and fire (LIF) model have been applied to energy-efficient temporal and spatiotemporal processing tasks. Due to the bioplausible neuronal dynamics and simplicity, LIF-SNN benefits from event-driven processing, however, usually face the embarrassment of reduced performance. This may because, in LIF-SNN, the neurons transmit information via spikes. To address this issue, in this work, we propose a leaky integrate and analog fire (LIAF) neuron model so that analog values can be transmitted among neurons, and a deep network termed LIAF-Net is built on it for efficient spatiotemporal processing. In the temporal domain, LIAF follows the traditional LIF dynamics to maintain its temporal processing capability. In the spatial domain, LIAF is able to integrate spatial information through convolutional integration or fully connected integration. As a spatiotemporal layer, LIAF can also be used with traditional artificial neural network (ANN) layers jointly. In addition, the built network can be trained with backpropagation through time (BPTT) directly, which avoids the performance loss caused by ANN to SNN conversion. Experiment results indicate that LIAF-Net achieves comparable performance to the gated recurrent unit (GRU) and long short-term memory (LSTM) on bAbI question answering (QA) tasks and achieves state-of-the-art performance on spatiotemporal dynamic vision sensor (DVS) data sets, including MNIST-DVS, CIFAR10-DVS, and DVS128 Gesture, with much less number of synaptic weights and computational overhead compared with traditional networks built by LSTM, GRU, convolutional LSTM (ConvLSTM), or 3-D convolution (Conv3D). Compared with traditional LIF-SNN, LIAF-Net also shows dramatic accuracy gain on all these experiments. In conclusion, LIAF-Net provides a framework combining the advantages of both ANNs and SNNs for lightweight and efficient spatiotemporal information processing.

An All-MRR-Based Photonic Spiking Neural Network for Spike Sequence Learning

Photonic spiking neural networks (SNN) have the advantages of high power efficiency, high bandwidth and low delay, but limitations are encountered in large-scale integration. The silicon photonics platform is a promising candidate for realizing large-scale photonic SNN because it is compatible with the current mature CMOS platforms. Here, we present an architecture of photonic SNN which consists of photonic neuron, photonic spike timing dependent plasticity (STDP) and weight configuration that are all based on silicon micro-ring resonators (MRRs), via taking advantage of the nonlinear effects in silicon. The photonic spiking neuron based on the add-drop MRR is proposed, and a system-level computational model of all-MRR-based photonic SNN is presented. The proposed architecture could exploit the properties of small area, high integration and flexible structure of MRR, but also faces challenges caused by the high sensitivity of MRR. The spike sequence learning problem is addressed based on the proposed all-MRR-based photonic SNN architecture via adopting supervised training algorithms. We show the importance of algorithms when hardware devices are limited.

SSTDP: Supervised Spike Timing Dependent Plasticity for Efficient Spiking Neural Network Training

Spiking Neural Networks (SNNs) are a pathway that could potentially empower low-power event-driven neuromorphic hardware due to their spatio-temporal information processing capability and high biological plausibility. Although SNNs are currently more efficient than artificial neural networks (ANNs), they are not as accurate as ANNs. Error backpropagation is the most common method for directly training neural networks, promoting the prosperity of ANNs in various deep learning fields. However, since the signals transmitted in the SNN are non-differentiable discrete binary spike events, the activation function in the form of spikes presents difficulties for the gradient-based optimization algorithms to be directly applied in SNNs, leading to a performance gap (i.e., accuracy and latency) between SNNs and ANNs. This paper introduces a new learning algorithm, called SSTDP, which bridges the gap between backpropagation (BP)-based learning and spike-time-dependent plasticity (STDP)-based learning to train SNNs efficiently. The scheme incorporates the global optimization process from BP and the efficient weight update derived from STDP. It not only avoids the non-differentiable derivation in the BP process but also utilizes the local feature extraction property of STDP. Consequently, our method can lower the possibility of vanishing spikes in BP training and reduce the number of time steps to reduce network latency. In SSTDP, we employ temporal-based coding and use Integrate-and-Fire (IF) neuron as the neuron model to provide considerable computational benefits. Our experiments show the effectiveness of the proposed SSTDP learning algorithm on the SNN by achieving the best classification accuracy 99.3% on the Caltech 101 dataset, 98.1% on the MNIST dataset, and 91.3% on the CIFAR-10 dataset compared to other SNNs trained with other learning methods. It also surpasses the best inference accuracy of the directly trained SNN with 25~32× less inference latency. Moreover, we analyze event-based computations to demonstrate the efficacy of the SNN for inference operation in the spiking domain, and SSTDP methods can achieve 1.3~37.7× fewer addition operations per inference. The code is available at: https://github.com/MXHX7199/SNN-SSTDP.

BlocTrain: Block-Wise Conditional Training and Inference for Efficient Spike-Based Deep Learning

Spiking neural networks (SNNs), with their inherent capability to learn sparse spike-based input representations over time, offer a promising solution for enabling the next generation of intelligent autonomous systems. Nevertheless, end-to-end training of deep SNNs is both compute- and memory-intensive because of the need to backpropagate error gradients through time. We propose BlocTrain, which is a scalable and complexity-aware incremental algorithm for memory-efficient training of deep SNNs. We divide a deep SNN into blocks, where each block consists of few convolutional layers followed by a classifier. We train the blocks sequentially using local errors from the classifier. Once a given block is trained, our algorithm dynamically figures out easy vs. hard classes using the class-wise accuracy, and trains the deeper block only on the hard class inputs. In addition, we also incorporate a hard class detector (HCD) per block that is used during inference to exit early for the easy class inputs and activate the deeper blocks only for the hard class inputs. We trained ResNet-9 SNN divided into three blocks, using BlocTrain, on CIFAR-10 and obtained 86.4% accuracy, which is achieved with up to 2.95× lower memory requirement during the course of training, and 1.89× compute efficiency per inference (due to early exit strategy) with 1.45× memory overhead (primarily due to classifier weights) compared to end-to-end network. We also trained ResNet-11, divided into four blocks, on CIFAR-100 and obtained 58.21% accuracy, which is one of the first reported accuracy for SNN trained entirely with spike-based backpropagation on CIFAR-100.

Spiking Neural Networks for Computational Intelligence: An Overview

Deep neural networks with rate-based neurons have exhibited tremendous progress in the last decade. However, the same level of progress has not been observed in research on spiking neural networks (SNN), despite their capability to handle temporal data, energy-efficiency and low latency. This could be because the benchmarking techniques for SNNs are based on the methods used for evaluating deep neural networks, which do not provide a clear evaluation of the capabilities of SNNs. Particularly, the benchmarking of SNN approaches with regards to energy efficiency and latency requires realization in suitable hardware, which imposes additional temporal and resource constraints upon ongoing projects. This review aims to provide an overview of the current real-world applications of SNNs and identifies steps to accelerate research involving SNNs in the future.

Stochastic binary synapses having sigmoidal cumulative distribution functions for unsupervised learning with spike timing-dependent plasticity

Spike timing-dependent plasticity (STDP), which is widely studied as a fundamental synaptic update rule for neuromorphic hardware, requires precise control of continuous weights. From the viewpoint of hardware implementation, a simplified update rule is desirable. Although simplified STDP with stochastic binary synapses was proposed previously, we find that it leads to degradation of memory maintenance during learning, which is unfavourable for unsupervised online learning. In this work, we propose a stochastic binary synaptic model where the cumulative probability of the weight change evolves in a sigmoidal fashion with potentiation or depression trials, which can be implemented using a pair of switching devices consisting of serially connected multiple binary memristors. As a benchmark test we perform simulations of unsupervised learning of MNIST images with a two-layer network and show that simplified STDP in combination with this model can outperform conventional rules with continuous weights not only in memory maintenance but also in recognition accuracy. Our method achieves 97.3% in recognition accuracy, which is higher than that reported with standard STDP in the same framework. We also show that the high performance of our learning rule is robust against device-to-device variability of the memristor's probabilistic behaviour.

Learning Invariant Object and Spatial View Representations in the Brain Using Slow Unsupervised Learning

First, neurophysiological evidence for the learning of invariant representations in the inferior temporal visual cortex is described. This includes object and face representations with invariance for position, size, lighting, view and morphological transforms in the temporal lobe visual cortex; global object motion in the cortex in the superior temporal sulcus; and spatial view representations in the hippocampus that are invariant with respect to eye position, head direction, and place. Second, computational mechanisms that enable the brain to learn these invariant representations are proposed. For the ventral visual system, one key adaptation is the use of information available in the statistics of the environment in slow unsupervised learning to learn transform-invariant representations of objects. This contrasts with deep supervised learning in artificial neural networks, which uses training with thousands of exemplars forced into different categories by neuronal teachers. Similar slow learning principles apply to the learning of global object motion in the dorsal visual system leading to the cortex in the superior temporal sulcus. The learning rule that has been explored in VisNet is an associative rule with a short-term memory trace. The feed-forward architecture has four stages, with convergence from stage to stage. This type of slow learning is implemented in the brain in hierarchically organized competitive neuronal networks with convergence from stage to stage, with only 4-5 stages in the hierarchy. Slow learning is also shown to help the learning of coordinate transforms using gain modulation in the dorsal visual system extending into the parietal cortex and retrosplenial cortex. Representations are learned that are in allocentric spatial view coordinates of locations in the world and that are independent of eye position, head direction, and the place where the individual is located. This enables hippocampal spatial view cells to use idiothetic, self-motion, signals for navigation when the view details are obscured for short periods.

Computing Primitive of Fully VCSEL-Based All-Optical Spiking Neural Network for Supervised Learning and Pattern Classification

We propose computing primitive for an all-optical spiking neural network (SNN) based on vertical-cavity surface-emitting lasers (VCSELs) for supervised learning by using biologically plausible mechanisms. The spike-timing-dependent plasticity (STDP) model was established based on the dynamics of the vertical-cavity semiconductor optical amplifier (VCSOA) subject to dual-optical pulse injection. The neuron-synapse self-consistent unified model of the all-optical SNN was developed, which enables reproducing the essential neuron-like dynamics and STDP function. Optical character numbers are trained and tested by the proposed fully VCSEL-based all-optical SNN. Simulation results show that the proposed all-optical SNN is capable of recognizing ten numbers by a supervised learning algorithm, in which the input and output patterns as well as the teacher signals of the all-optical SNN are represented by spatiotemporal fashions. Moreover, the lateral inhibition is not required in our proposed architecture, which is friendly to the hardware implementation. The system-level unified model enables architecture-algorithm codesigns and optimization of all-optical SNN. To the best of our knowledge, the computing primitive of an all-optical SNN based on VCSELs for supervised learning has not yet been reported, which paves the way toward fully VCSEL-based large-scale photonic neuromorphic systems with low power consumption.

Helix Matrix Transformation Combined With Convolutional Neural Network Algorithm for Matrix-Assisted Laser Desorption Ionization-Time of Flight Mass Spectrometry-Based Bacterial Identification

Matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) analysis is a rapid and reliable method for bacterial identification. Classification algorithms, as a critical part of the MALDI-TOF MS analysis approach, have been developed using both traditional algorithms and machine learning algorithms. In this study, a method that combined helix matrix transformation with a convolutional neural network (CNN) algorithm was presented for bacterial identification. A total of 14 bacterial species including 58 strains were selected to create an in-house MALDI-TOF MS spectrum dataset. The 1D array-type MALDI-TOF MS spectrum data were transformed through a helix matrix transformation into matrix-type data, which was fitted during the CNN training. Through the parameter optimization, the threshold for binarization was set as 16 and the final size of a matrix-type data was set as 25 × 25 to obtain a clean dataset with a small size. A CNN model with three convolutional layers was well trained using the dataset to predict bacterial species. The filter sizes for the three convolutional layers were 4, 8, and 16. The kernel size was three and the activation function was the rectified linear unit (ReLU). A back propagation neural network (BPNN) model was created without helix matrix transformation and a convolution layer to demonstrate whether the helix matrix transformation combined with CNN algorithm works better. The areas under the receiver operating characteristic (ROC) curve of the CNN and BPNN models were 0.98 and 0.87, respectively. The accuracies of the CNN and BPNN models were 97.78 ± 0.08 and 86.50 ± 0.01, respectively, with a significant statistical difference (p < 0.001). The results suggested that helix matrix transformation combined with the CNN algorithm enabled the feature extraction of the bacterial MALDI-TOF MS spectrum, which might be a proposed solution to identify bacterial species.

Sparse coding with a somato-dendritic rule

Cortical neurons are silent most of the time: sparse activity enables low-energy computation in the brain, and promises to do the same in neuromorphic hardware. Beyond power efficiency, sparse codes have favourable properties for associative learning, as they can store more information than local codes but are easier to read out than dense codes. Auto-encoders with a sparse constraint can learn sparse codes, and so can single-layer networks that combine recurrent inhibition with unsupervised Hebbian learning. But the latter usually require fast homeostatic plasticity, which could lead to catastrophic forgetting in embodied agents that learn continuously. Here we set out to explore whether plasticity at recurrent inhibitory synapses could take up that role instead, regulating both the population sparseness and the firing rates of individual neurons. We put the idea to the test in a network that employs compartmentalised inputs to solve the task: rate-based dendritic compartments integrate the feedforward input, while spiking integrate-and-fire somas compete through recurrent inhibition. A somato-dendritic learning rule allows somatic inhibition to modulate nonlinear Hebbian learning in the dendrites. Trained on MNIST digits and natural images, the network discovers independent components that form a sparse encoding of the input and support linear decoding. These findings confirm that intrinsic homeostatic plasticity is not strictly required for regulating sparseness: inhibitory synaptic plasticity can have the same effect. Our work illustrates the usefulness of compartmentalised inputs, and makes the case for moving beyond point neuron models in artificial spiking neural networks.

Bio-Inspired Techniques in a Fully Digital Approach for Lifelong Learning

Lifelong learning has deeply underpinned the resilience of biological organisms respect to a constantly changing environment. This flexibility has allowed the evolution of parallel-distributed systems able to merge past information with new stimulus for accurate and efficient brain-computation. Nowadays, there is a strong attempt to reproduce such intelligent systems in standard artificial neural networks (ANNs). However, despite some great results in specific tasks, ANNs still appear too rigid and static in real life respect to the biological systems. Thus, it is necessary to define a new neural paradigm capable of merging the lifelong resilience of biological organisms with the great accuracy of ANNs. Here, we present a digital implementation of a novel mixed supervised-unsupervised neural network capable of performing lifelong learning. The network uses a set of convolutional filters to extract features from the input images of the MNIST and the Fashion-MNIST training datasets. This information defines an original combination of responses of both trained classes and non-trained classes by transfer learning. The responses are then used in the subsequent unsupervised learning based on spike-timing dependent plasticity (STDP). This procedure allows the clustering of non-trained information thanks to bio-inspired algorithms such as neuronal redundancy and spike-frequency adaptation. We demonstrate the implementation of the neural network in a fully digital environment, such as the Xilinx Zynq-7000 System on Chip (SoC). We illustrate a user-friendly interface to test the network by choosing the number and the type of the non-trained classes, or drawing a custom pattern on a tablet. Finally, we propose a comparison of this work with networks based on memristive synaptic devices capable of continual learning, highlighting the main differences and capabilities respect to a fully digital approach.

Impact of the Sub-Resting Membrane Potential on Accurate Inference in Spiking Neural Networks

Spiking neural networks (SNNs) are considered as the third generation of artificial neural networks, having the potential to improve the energy efficiency of conventional computing systems. Although the firing rate of a spiking neuron is an approximation of rectified linear unit (ReLU) activation in an analog-valued neural network (ANN), there remain many challenges to be overcome owing to differences in operation between ANNs and SNNs. Unlike actual biological and biophysical processes, various hardware implementations of neurons and SNNs do not allow the membrane potential to fall below the resting potential—in other words, neurons must allow the sub-resting membrane potential. Because there occur an excitatory post-synaptic potential (EPSP) as well as an inhibitory post-synaptic potential (IPSP), negatively valued synaptic weights in SNNs induce the sub-resting membrane potential at some time point. If a membrane is not allowed to hold the sub-resting potential, errors will accumulate over time, resulting in inaccurate inference operations. This phenomenon is not observed in ANNs given their use of only spatial synaptic integration, but it can cause serious performance degradation in SNNs. In this paper, we demonstrate the impact of the sub-resting membrane potential on accurate inference operations in SNNs. Moreover, several important considerations for a hardware SNN that can maintain the sub-resting membrane potential are discussed. All of the results in this paper indicate that it is essential for neurons to allow the sub-resting membrane potential in order to realize high-performance SNNs.

Spike Counts Based Low Complexity SNN Architecture With Binary Synapse

In this paper, we present an energy and area efficient spike neural network (SNN) processor based on novel spike counts based methods. For the low cost SNN design, we propose hardware-friendly complexity reduction techniques for both of learning and inferencing modes of operations. First, for the unsupervised learning process, we propose a spike counts based learning method. The novel learning approach utilizes pre- and post-synaptic spike counts to reduce the bit-width of synaptic weights as well as the number of weight updates. For the energy efficient inferencing operations, we propose an accumulation based computing scheme, where the number of input spikes for each input axon is accumulated without instant membrane updates until the pre-defined number of spikes are reached. In addition, the computation skip schemes identify meaningless computations and skip them to improve energy efficiency. Based on the proposed low complexity design techniques, we design and implement the SNN processor using 65 nm CMOS process. According to the implementation results, the SNN processor achieves 87.4% of recognition accuracy in MNIST dataset using only 1-bit 230 k synaptic weights with 400 excitatory neurons. The energy consumptions are 0.26 pJ/SOP and 0.31 μJ/inference in inferencing mode, and 1.42 pJ/SOP and 2.63 μJ/learning in learning mode of operations.

A Hardware-Deployable Neuromorphic Solution for Encoding and Classification of Electronic Nose Data

In several application domains, electronic nose systems employing conventional data processing approaches incur substantial power and computational costs and limitations, such as significant latency and poor accuracy for classification. Recent developments in spike-based bio-inspired approaches have delivered solutions for the highly accurate classification of multivariate sensor data with minimized computational and power requirements. Although these methods have addressed issues related to efficient data processing and classification accuracy, other areas, such as reducing the processing latency to support real-time application and deploying spike-based solutions on supported hardware, have yet to be studied in detail. Through this investigation, we proposed a spiking neural network (SNN)-based classifier, implemented in a chip-emulation-based development environment, that can be seamlessly deployed on a neuromorphic system-on-a-chip (NSoC). Under three different scenarios of increasing complexity, the SNN was determined to be able to classify real-valued sensor data with greater than 90% accuracy and with a maximum latency of 3 s on the software-based platform. Highlights of this work included the design and implementation of a novel encoder for artificial olfactory systems, implementation of unsupervised spike-timing-dependent plasticity (STDP) for learning, and a foundational study on early classification capability using the SNN-based classifier.

SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks With at Most One Spike per Neuron

Application of deep convolutional spiking neural networks (SNNs) to artificial intelligence (AI) tasks has recently gained a lot of interest since SNNs are hardware-friendly and energy-efficient. Unlike the non-spiking counterparts, most of the existing SNN simulation frameworks are not practically efficient enough for large-scale AI tasks. In this paper, we introduce SpykeTorch, an open-source high-speed simulation framework based on PyTorch. This framework simulates convolutional SNNs with at most one spike per neuron and the rank-order encoding scheme. In terms of learning rules, both spike-timing-dependent plasticity (STDP) and reward-modulated STDP (R-STDP) are implemented, but other rules could be implemented easily. Apart from the aforementioned properties, SpykeTorch is highly generic and capable of reproducing the results of various studies. Computations in the proposed framework are tensor-based and totally done by PyTorch functions, which in turn brings the ability of just-in-time optimization for running on CPUs, GPUs, or Multi-GPU platforms.

A Soft-Pruning Method Applied During Training of Spiking Neural Networks for In-memory Computing Applications

Inspired from the computational efficiency of the biological brain, spiking neural networks (SNNs) emulate biological neural networks, neural codes, dynamics, and circuitry. SNNs show great potential for the implementation of unsupervised learning using in-memory computing. Here, we report an algorithmic optimization that improves energy efficiency of online learning with SNNs on emerging non-volatile memory (eNVM) devices. We develop a pruning method for SNNs by exploiting the output firing characteristics of neurons. Our pruning method can be applied during network training, which is different from previous approaches in the literature that employ pruning on already-trained networks. This approach prevents unnecessary updates of network parameters during training. This algorithmic optimization can complement the energy efficiency of eNVM technology, which offers a unique in-memory computing platform for the parallelization of neural network operations. Our SNN maintains ~90% classification accuracy on the MNIST dataset with up to ~75% pruning, significantly reducing the number of weight updates. The SNN and pruning scheme developed in this work can pave the way toward applications of eNVM based neuro-inspired systems for energy efficient online learning in low power applications.

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.

BindsNET: A Machine Learning-Oriented Spiking Neural Networks Library in Python

The development of spiking neural network simulation software is a critical component enabling the modeling of neural systems and the development of biologically inspired algorithms. Existing software frameworks support a wide range of neural functionality, software abstraction levels, and hardware devices, yet are typically not suitable for rapid prototyping or application to problems in the domain of machine learning. In this paper, we describe a new Python package for the simulation of spiking neural networks, specifically geared toward machine learning and reinforcement learning. Our software, called BindsNET, enables rapid building and simulation of spiking networks and features user-friendly, concise syntax. BindsNET is built on the PyTorch deep neural networks library, facilitating the implementation of spiking neural networks on fast CPU and GPU computational platforms. Moreover, the BindsNET framework can be adjusted to utilize other existing computing and hardware backends; e.g., TensorFlow and SpiNNaker. We provide an interface with the OpenAI gym library, allowing for training and evaluation of spiking networks on reinforcement learning environments. We argue that this package facilitates the use of spiking networks for large-scale machine learning problems and show some simple examples by using BindsNET in practice.

Memristive Spiking Neural Networks Trained with Unsupervised STDP

Neuromorphic computing systems are promising alternatives in the fields of pattern recognition, image processing, etc. especially when conventional von Neumann architectures face several bottlenecks. Memristors play vital roles in neuromorphic computing systems and are usually used as synaptic devices. Memristive spiking neural networks (MSNNs) are considered to be more efficient and biologically plausible than other systems due to their spike-based working mechanism. In contrast to previous SNNs with complex architectures, we propose a hardware-friendly architecture and an unsupervised spike-timing dependent plasticity (STDP) learning method for MSNNs in this paper. The architecture, which is friendly to hardware implementation, includes an input layer, a feature learning layer and a voting circuit. To reduce hardware complexity, some constraints are enforced: the proposed architecture has no lateral inhibition and is purely feedforward; it uses the voting circuit as a classifier and does not use additional classifiers; all neurons can generate at most one spike and do not need to consider firing rates and refractory periods; all neurons have the same fixed threshold voltage for classification. The presented unsupervised STDP learning method is time-dependent and uses no homeostatic mechanism. The MNIST dataset is used to demonstrate our proposed architecture and learning method. Simulation results show that our proposed architecture with the learning method achieves a classification accuracy of 94.6%, which outperforms other unsupervised SNNs that use time-based encoding schemes.

SpiLinC: Spiking Liquid-Ensemble Computing for Unsupervised Speech and Image Recognition

In this work, we propose a Spiking Neural Network (SNN) consisting of input neurons sparsely connected by plastic synapses to a randomly interlinked liquid, referred to as Liquid-SNN, for unsupervised speech and image recognition. We adapt the strength of the synapses interconnecting the input and liquid using Spike Timing Dependent Plasticity (STDP), which enables the neurons to self-learn a general representation of unique classes of input patterns. The presented unsupervised learning methodology makes it possible to infer the class of a test input directly using the liquid neuronal spiking activity. This is in contrast to standard Liquid State Machines (LSMs) that have fixed synaptic connections between the input and liquid followed by a readout layer (trained in a supervised manner) to extract the liquid states and infer the class of the input patterns. Moreover, the utility of LSMs has primarily been demonstrated for speech recognition. We find that training such LSMs is challenging for complex pattern recognition tasks because of the information loss incurred by using fixed input to liquid synaptic connections. We show that our Liquid-SNN is capable of efficiently recognizing both speech and image patterns by learning the rich temporal information contained in the respective input patterns. However, the need to enlarge the liquid for improving the accuracy introduces scalability challenges and training inefficiencies. We propose SpiLinC that is composed of an ensemble of multiple liquids operating in parallel. We use a “divide and learn” strategy for SpiLinC, where each liquid is trained on a unique segment of the input patterns that causes the neurons to self-learn distinctive input features. SpiLinC effectively recognizes a test pattern by combining the spiking activity of the constituent liquids, each of which identifies characteristic input features. As a result, SpiLinC offers competitive classification accuracy compared to the Liquid-SNN with added sparsity in synaptic connectivity and faster training convergence, both of which lead to improved energy efficiency in neuromorphic hardware implementations. We validate the efficacy of the proposed Liquid-SNN and SpiLinC on the entire digit subset of the TI46 speech corpus and handwritten digits from the MNIST dataset.

Training Deep Spiking Convolutional Neural Networks With STDP-Based Unsupervised Pre-training Followed by Supervised Fine-Tuning

Spiking Neural Networks (SNNs) are fast becoming a promising candidate for brain-inspired neuromorphic computing because of their inherent power efficiency and impressive inference accuracy across several cognitive tasks such as image classification and speech recognition. The recent efforts in SNNs have been focused on implementing deeper networks with multiple hidden layers to incorporate exponentially more difficult functional representations. In this paper, we propose a pre-training scheme using biologically plausible unsupervised learning, namely Spike-Timing-Dependent-Plasticity (STDP), in order to better initialize the parameters in multi-layer systems prior to supervised optimization. The multi-layer SNN is comprised of alternating convolutional and pooling layers followed by fully-connected layers, which are populated with leaky integrate-and-fire spiking neurons. We train the deep SNNs in two phases wherein, first, convolutional kernels are pre-trained in a layer-wise manner with unsupervised learning followed by fine-tuning the synaptic weights with spike-based supervised gradient descent backpropagation. Our experiments on digit recognition demonstrate that the STDP-based pre-training with gradient-based optimization provides improved robustness, faster (~2.5 ×) training time and better generalization compared with purely gradient-based training without pre-training.