Human-Level Control through Directly-Trained Deep Spiking Q-Networks
South-western University of Finance and Economics（西南财经大学）；Zhongshan Institute, University of Electronic Science and Technology of China（电子科技大学中山学院）；University of Electronic Science and Technology of China（电子科技大学）；Zhejiang University（浙江大学）；Zhejiang Laboratory（之江实验室）
Guisong Liu, Wenjie Deng, Xiurui Xie, Li Huang, Huajin Tang
As the third-generation neural networks, Spiking Neural Networks (SNNs) have great potential on neuromorphic hardware because of their high energy-efficiency. However, Deep Spiking Reinforcement Learning (DSRL), i.e., the Reinforcement Learning (RL) based on SNNs, is still in its preliminary stage due to the binary output and the non-differentiable property of the spiking function. To address these issues, we propose a Deep Spiking Q-Network (DSQN) in this paper. Specifically, we propose a directly-trained deep spiking reinforcement learning architecture based on the Leaky Integrate-and-Fire (LIF) neurons and Deep Q-Network (DQN). Then, we adapt a direct spiking learning algorithm for the Deep Spiking Q-Network. We further demonstrate the advantages of using LIF neurons in DSQN theoretically. Comprehensive experiments have been conducted on 17 top-performing Atari games to compare our method with the state-of-the-art conversion method. The experimental results demonstrate the superiority of our method in terms of performance, stability, robustness and energy-efficiency. To the best of our knowledge, our work is the first one to achieve state-of-the-art performance on multiple Atari games with the directly-trained SNN.
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；University of Memphis（孟菲斯大学）
Deep Reinforcement Learning (RL) demonstrates excellent performance on tasks that can be solved by trained policy. It plays a dominant role among cutting-edge machine learning approaches using multi-layer Neural networks (NNs). At the same time, Deep RL suffers from high sensitivity to noisy, incomplete, and misleading input data. Following biological intuition, we involve Spiking Neural Networks (SNNs) to address some deficiencies of deep RL solutions. Previous studies in image classification domain demonstrated that standard NNs (with ReLU nonlinearity) trained using supervised learning can …
Computational Brain Lab, Department of Computer Science, Rutgers University（罗格斯大学计算机科学系计算大脑实验室）
Energy-efficient mapless navigation is crucial for mobile robots as they explore unknown environments with limited on-board resources. Although the recent deep reinforcement learning (DRL) approaches have been successfully applied to navigation, their high energy consumption limits their use in several robotic applications. Here, we propose a neuromorphic approach that combines the energy-efficiency of spiking neural networks with the optimality of DRL and benchmark it in learning control policies for mapless navigation. Our hybrid framework, spiking deep deterministic policy gradient (SDDPG),…
The energy-efficient control of mobile robots is crucial as the complexity of their real-world applications increasingly involves high-dimensional observation and action spaces, which cannot be offset by limited on-board resources. An emerging non-Von Neumann model of intelligence, where spiking neural networks (SNNs) are run on neuromorphic processors, is regarded as an energy-efficient and robust alternative to the state-of-the-art real-time robotic controllers for low dimensional control tasks. The challenge now for this new computing paradigm is to scale so that it can keep up with real-wo…
Research Center for Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所类脑智能研究中心）；School of Future Technology, University of Chinese Academy of Sciences（中国科学院大学未来技术学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）；Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences（中国科学院脑科学与智能技术卓越创新中心）
Brain inspired spiking neural networks (SNNs) have been successfully applied to many pattern recognition domains. The SNNs based deep structure have achieved considerable results in perceptual tasks, such as image classification, target detection. However, the application of deep SNNs in reinforcement learning (RL) tasks is still a problem to be explored. Although there have been previous studies on the combination of SNNs and RL, most of them focus on robotic control problems with shallow networks or using ANN-SNN conversion method to implement spiking deep Q Network (SDQN). In this work, we …
In this work we explore recurrent representations of leaky integrate and fire neurons operating at a timescale equal to their absolute refractory period. Our coarse time scale approximation is obtained using a probability distribution function for spike arrivals that is homogeneously distributed over this time interval. This leads to a discrete representation that exhibits the same dynamics as the continuous model, enabling efficient large scale simulations and backpropagation through the recurrent implementation. We use this approach to explore the training of deep spiking neural networks inc…
Purdue University（普渡大学）；Nanoelectronics Research Laboratory（纳米电子学研究实验室）
Spiking Neural Networks (SNNs) are being explored for their potential energy efficiency resulting from sparse, event-driven computations. Many recent works have demonstrated effective backpropagation for deep Spiking Neural Networks (SNNs) by approximating gradients over discontinuous neuron spikes or firing events. A beneficial side-effect of these surrogate gradient spiking backpropagation algorithms is that the spikes, which trigger additional computations, may now themselves be directly considered in the gradient calculations. We propose an explicit inclusion of spike counts in the loss fu…
Gradient descent training techniques are remarkably successful in training analog-valued artificial neural networks (ANNs). Such training techniques, however, do not transfer easily to spiking networks due to the spike generation hard non-linearity and the discrete nature of spike communication. We show that in a feedforward spiking network that uses a temporal coding scheme where information is encoded in spike times instead of spike rates, the network input-output relation is differentiable almost everywhere. Moreover, this relation is piece-wise linear after a transformation of variables. M…
Recent advances in Voice Activity Detection (VAD) are driven by artificial and Recurrent Neural Networks (RNNs), however, using a VAD system in battery-operated devices requires further power efficiency. This can be achieved by neuromorphic hardware, which enables Spiking Neural Networks (SNNs) to perform inference at very low energy consumption. Spiking networks are characterized by their ability to process information efficiently, in a sparse cascade of binary events in time called spikes. However, a big performance gap separates artificial from spiking networks, mostly due to a lack of powe…
A Spiking Neural Network (SNN) is trained with Spike Timing Dependent Plasticity (STDP), which is a neuro-inspired unsupervised learning method for various machine learning applications. This paper studies the generalizability properties of the STDP learning processes using the Hausdorff dimension of the trajectories of the learning algorithm. The paper analyzes the effects of STDP learning models and associated hyper-parameters on the generalizability properties of an SNN. The analysis is used to develop a Bayesian optimization approach to optimize the hyper-parameters for an STDP model for i…
Artificial neural networks (ANNs) experience catastrophic forgetting (CF) during sequential learning. In contrast, the brain can learn continuously without any signs of catastrophic forgetting. Spiking neural networks (SNNs) are the next generation of ANNs with many features borrowed from biological neural networks. Thus, SNNs potentially promise better resilience to CF. In this paper, we study the susceptibility of SNNs to CF and test several biologically inspired methods for mitigating catastrophic forgetting. SNNs are trained with biologically plausible local training rules based on spike-t…
Spiking neural networks are biologically plausible counterparts of the artificial neural networks, artificial neural networks are usually trained with stochastic gradient descent and spiking neural networks are trained with spike timing dependant plasticity. Training deep convolutional neural networks is a memory and power intensive job. Spiking networks could potentially help in reducing the power usage. There is a large pool of tools for one to chose to train artificial neural networks of any size, on the other hand all the available tools to simulate spiking neural networks are geared towar…
Spiking Neural Network (SNN), as a brain-inspired approach, is attracting attention due to its potential to produce ultra-high-energy-efficient hardware. Competitive learning based on Spike-Timing-Dependent Plasticity (STDP) is a popular method to train an unsupervised SNN. However, previous unsupervised SNNs trained through this method are limited to a shallow network with only one learnable layer and cannot achieve satisfactory results when compared with multi-layer SNNs. In this paper, we eased this limitation by: 1)We proposed a Spiking Inception (Sp-Inception) module, inspired by the Ince…
Spiking Neural Networks are often touted as brain-inspired learning models for the third wave of Artificial Intelligence. Although recent SNNs trained with supervised backpropagation show classification accuracy comparable to deep networks, the performance of unsupervised learning-based SNNs remains much lower. This paper presents a heterogeneous recurrent spiking neural network (HRSNN) with unsupervised learning for spatio-temporal classification of video activity recognition tasks on RGB (KTH, UCF11, UCF101) and event-based datasets (DVS128 Gesture). The key novelty of the HRSNN is that the …
The event-driven and sparse nature of communication between spiking neurons in the brain holds great promise for flexible and energy-efficient AI. Recent advances in learning algorithms have demonstrated that recurrent networks of spiking neurons can be effectively trained to achieve competitive performance compared to standard recurrent neural networks. Still, as these learning algorithms use error-backpropagation through time (BPTT), they suffer from high memory requirements, are slow to train, and are incompatible with online learning. This limits the application of these learning algorithm…
Brigham Young University–Idaho（爱达荷州杨百翰大学）；Purdue University（普渡大学）
Spiking Neural Networks (SNNs) are being explored for their potential energy efficiency benefits due to sparse, event-driven computation. Non-spiking artificial neural networks are typically trained with stochastic gradient descent using backpropagation. The calculation of true gradients for backpropagation in spiking neural networks is impeded by the non-differentiable firing events of spiking neurons. On the other hand, using approximate gradients is effective, but computationally expensive over many time steps. One common technique, then, for training a spiking neural network is to train a …
The increasing need for intelligent sensors in a wide range of everyday objects requires the existence of low power information processing systems which can operate autonomously in their environment. In particular, merging and processing the outputs of different sensors efficiently is a necessary requirement for mobile agents with cognitive abilities. In this work, we present a multi-layer spiking neural network for inference of relations between stimuli patterns in dedicated neuromorphic systems. The system is trained with a new version of the backpropagation algorithm adapted to on-chip lear…
University of Minnesota（明尼苏达大学）；University of Surrey（萨里大学）；University of Applied Sciences, Stralsund（施特拉尔松德应用科学大学）
In this work we propose a new supervised learning method for temporally-encoded multilayer spiking networks to perform classification. The method employs a reinforcement signal that mimics backpropagation but is far less computationally intensive. The weight update calculation at each layer requires only local data apart from this signal. We also employ a rule capable of producing specific output spike trains; by setting the target spike time equal to the actual spike time with a slight negative offset for key high-value neurons the actual spike time becomes as early as possible. In simulated …
We present a system comprising a hybridization of self-organized map (SOM) properties with spiking neural networks (SNNs) that retain many of the features of SOMs. Networks are trained in an unsupervised manner to learn a self-organized lattice of filters via excitatory-inhibitory interactions among populations of neurons. We develop and test various inhibition strategies, such as growing with inter-neuron distance and two distinct levels of inhibition. The quality of the unsupervised learning algorithm is evaluated using examples with known labels. Several biologically-inspired classification…
IBM Research Europe – Zurich（IBM欧洲研究院-苏黎世）；École polytechnique fédérale de Lausanne（洛桑联邦理工学院）
Deep spiking neural networks (SNNs) offer the promise of low-power artificial intelligence. However, training deep SNNs from scratch or converting deep artificial neural networks to SNNs without loss of performance has been a challenge. Here we propose an exact mapping from a network with Rectified Linear Units (ReLUs) to an SNN that fires exactly one spike per neuron. For our constructive proof, we assume that an arbitrary multi-layer ReLU network with or without convolutional layers, batch normalization and max pooling layers was trained to high performance on some training set. Furthermore,…
In this work, we explore a new Spiking Neural Network (SNN) formulation with Resonate-and-Fire (RAF) neurons (Izhikevich, 2001) trained with gradient descent via back-propagation. The RAF-SNN, while more biologically plausible, achieves performance comparable to or higher than conventional models in the Machine Learning literature across different network configurations, using similar or fewer parameters. Strikingly, the RAF-SNN proves robust against noise induced at testing/training time, under both static and dynamic conditions. Against CNN on MNIST, we show 25% higher absolute accuracy with…
Brown University（布朗大学）；Pacific Northwest National Laboratory（太平洋西北国家实验室）
We propose a Spiking Neural Network (SNN)-based explicit numerical scheme for long time integration of time-dependent Ordinary and Partial Differential Equations (ODEs, PDEs). The core element of the method is a SNN, trained to use spike-encoded information about the solution at previous timesteps to predict spike-encoded information at the next timestep. After the network has been trained, it operates as an explicit numerical scheme that can be used to compute the solution at future timesteps, given a spike-encoded initial condition. A decoder is used to transform the evolved spiking-encoded …
Energy-Efficient Eimeria Parasite Detection Using a Two-Stage Spiking Neural Network Architecture
Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI)（数据科学与计算智能安达卢西亚研究机构）；University of Jaén（杰内大学）；Department of Information Systems, College of Computing and Informatics（信息系统系，计算与信息科学学院）；University of Sharjah（沙迦大学）；Department of Computer Science, School of Architecture, Built Environment, Computing, and Engineering（计算机科学系，建筑、环境、计算与工程学院）；Birmingham City University（伯明翰城市大学）
University of Electronic Science and Technology of China（电子科技大学）；Yale University（耶鲁大学）；Harvard University（哈佛大学）
Spiking Neural Network (SNN), originating from the neural behavior in biology, has been recognized as one of the next-generation neural networks. Conventionally, SNNs can be obtained by converting from pre-trained Artificial Neural Networks (ANNs) by replacing the non-linear activation with spiking neurons without changing the parameters. In this work, we argue that simply copying and pasting the weights of ANN to SNN inevitably results in activation mismatch, especially for ANNs that are trained with batch normalization (BN) layers. To tackle the activation mismatch issue, we first provide a …
We propose that in order to harness our understanding of neuroscience toward machine learning, we must first have powerful tools for training brain-like models of learning. Although substantial progress has been made toward understanding the dynamics of learning in the brain, neuroscience-derived models of learning have yet to demonstrate the same performance capabilities as methods in deep learning such as gradient descent. Inspired by the successes of machine learning using gradient descent, we demonstrate that models of neuromodulated synaptic plasticity from neuroscience can be trained in …
Peter Grünberg Institute – Neuromorphic Software Ecosystems（彼得·格伦贝格研究所——神经形态软件生态系统）；Forschungszentrum Jülich（于利希研究中心）；RWTH Aachen（亚琛工业大学）；UC Irvine（加州大学欧文分校）
Adaptive "life-long" learning at the edge and during online task performance is an aspirational goal of AI research. Neuromorphic hardware implementing Spiking Neural Networks (SNNs) are particularly attractive in this regard, as their real-time, event-based, local computing paradigm makes them suitable for edge implementations and fast learning. However, the long and iterative learning that characterizes state-of-the-art SNN training is incompatible with the physical nature and real-time operation of neuromorphic hardware. Bi-level learning, such as meta-learning is increasingly used in deep …
In the last few years, spiking neural networks have been demonstrated to perform on par with regular convolutional neural networks. Several works have proposed methods to convert a pre-trained CNN to a Spiking CNN without a significant sacrifice of performance. We demonstrate first that quantization-aware training of CNNs leads to better accuracy in SNNs. One of the benefits of converting CNNs to spiking CNNs is to leverage the sparse computation of SNNs and consequently perform equivalent computation at a lower energy consumption. Here we propose an efficient optimization strategy to train sp…
Memristors have been suggested as neuromorphic computing elements. Spike-time dependent plasticity and the Hodgkin-Huxley model of the neuron have both been modelled effectively by memristor theory. The d.c. response of the memristor is a current spike. Based on these three facts we suggest that memristors are well-placed to interface directly with neurons. In this paper we show that connecting a spiking memristor network to spiking neuronal cells causes a change in the memristor network dynamics by: removing the memristor spikes, which we show is due to the effects of connection to aqueous me…
Bio-inspired spiking neural networks (SNNs), operating with asynchronous binary signals (or spikes) distributed over time, can potentially lead to greater computational efficiency on event-driven hardware. The state-of-the-art SNNs suffer from high inference latency, resulting from inefficient input encoding, and sub-optimal settings of the neuron parameters (firing threshold, and membrane leak). We propose DIET-SNN, a low-latency deep spiking network that is trained with gradient descent to optimize the membrane leak and the firing threshold along with other network parameters (weights). The …
As the scales of neural networks increase, techniques that enable them to run with low computational cost and energy efficiency are required. From such demands, various efficient neural network paradigms, such as spiking neural networks (SNNs) or binary neural networks (BNNs), have been proposed. However, they have sticky drawbacks, such as degraded inference accuracy and latency. To solve these problems, we propose a single-step spiking neural network (S$^3$NN), an energy-efficient neural network with low computational cost and high precision. The proposed S$^3$NN processes the information be…
Shahid Beheshti University（沙希德·贝赫什提大学）；Amirkabir University of Technology（阿米尔卡比尔理工大学）；CNRS（法国国家科学研究中心）；Université Toulouse 3（图卢兹第三大学）
We propose a new learning algorithm to train spiking neural networks (SNN) using conventional artificial neural networks (ANN) as proxy. We couple two SNN and ANN networks, respectively, made of integrate-and-fire (IF) and ReLU neurons with the same network architectures and shared synaptic weights. The forward passes of the two networks are totally independent. By assuming IF neuron with rate-coding as an approximation of ReLU, we backpropagate the error of the SNN in the proxy ANN to update the shared weights, simply by replacing the ANN final output with that of the SNN. We applied the prop…
Seoul National University（首尔国立大学）；Stanford University（斯坦福大学）
Nowadays deep learning is dominating the field of machine learning with state-of-the-art performance in various application areas. Recently, spiking neural networks (SNNs) have been attracting a great deal of attention, notably owning to their power efficiency, which can potentially allow us to implement a low-power deep learning engine suitable for real-time/mobile applications. However, implementing SNN-based deep learning remains challenging, especially gradient-based training of SNNs by error backpropagation. We cannot simply propagate errors through SNNs in conventional way because of the…
A new supervised learning algorithm, SNN/LP, is proposed for Spiking Neural Networks. This novel algorithm uses limited precision for both synaptic weights and synaptic delays; 3 bits in each case. Also a genetic algorithm is used for the supervised training. The results are comparable or better than previously published work. The results are applicable to the realization of large scale hardware neural networks. One of the trained networks is implemented in programmable hardware.
Deep Spiking Neural Networks (SNNs) present optimization difficulties for gradient-based approaches due to discrete binary activation and complex spatial-temporal dynamics. Considering the huge success of ResNet in deep learning, it would be natural to train deep SNNs with residual learning. Previous Spiking ResNet mimics the standard residual block in ANNs and simply replaces ReLU activation layers with spiking neurons, which suffers the degradation problem and can hardly implement residual learning. In this paper, we propose the spike-element-wise (SEW) ResNet to realize residual learning in…
We present a fully memristive spiking neural network (MSNN) consisting of novel memristive neurons trained using the backpropagation through time (BPTT) learning rule. Gradient descent is applied directly to the memristive integrated-and-fire (MIF) neuron designed using analog SPICE circuit models, which generates distinct depolarization, hyperpolarization, and repolarization voltage waveforms. Synaptic weights are trained by BPTT using the membrane potential of the MIF neuron model and can be processed on memristive crossbars. The natural spiking dynamics of the MIF neuron model are fully dif…
Spiking neural networks have shown great promise for the design of low-power sensory-processing and edge-computing hardware platforms. However, implementing on-chip learning algorithms on such architectures is still an open challenge, especially for multi-layer networks that rely on the back-propagation algorithm. In this paper, we present a spike-based learning method that approximates back-propagation using local weight update mechanisms and which is compatible with mixed-signal analog/digital neuromorphic circuits. We introduce a network architecture that enables synaptic weight update mech…
Spiking neural networks are motivated from principles of neural systems and may possess unexplored advantages in the context of machine learning. A class of \textit{convolutional spiking neural networks} is introduced, trained to detect image features with an unsupervised, competitive learning mechanism. Image features can be shared within subpopulations of neurons, or each may evolve independently to capture different features in different regions of input space. We analyze the time and memory requirements of learning with and operating such networks. The MNIST dataset is used as an experimen…
The spiking neural networks (SNNs) are considered as one of the most promising artificial neural networks due to their energy efficient computing capability. Recently, conversion of a trained deep neural network to an SNN has improved the accuracy of deep SNNs. However, most of the previous studies have not achieved satisfactory results in terms of inference speed and energy efficiency. In this paper, we propose a fast and energy-efficient information transmission method with burst spikes and hybrid neural coding scheme in deep SNNs. Our experimental results showed the proposed methods can imp…
Compared with rate-based artificial neural networks, Spiking Neural Networks (SNN) provide a more biological plausible model for the brain. But how they perform supervised learning remains elusive. Inspired by recent works of Bengio et al., we propose a supervised learning algorithm based on Spike-Timing Dependent Plasticity (STDP) for a hierarchical SNN consisting of Leaky Integrate-and-fire (LIF) neurons. A time window is designed for the presynaptic neuron and only the spikes in this window take part in the STDP updating process. The model is trained on the MNIST dataset. The classification…
The brain is known to be a highly complex, asynchronous dynamical system that is highly tailored to encode temporal information. However, recent deep learning approaches to not take advantage of this temporal coding. Spiking Neural Networks (SNNs) can be trained using biologically-realistic learning mechanisms, and can have neuronal activation rules that are biologically relevant. This type of network is also structured fundamentally around accepting temporal information through a time-decaying voltage update, a kind of input that current rate-encoding networks have difficulty with. Here we sh…
