Toward Efficient Processing and Learning With Spikes: New Approaches for Multispike Learning

Improving Multispike Learning With Plastic Synaptic Delays

Emulating the spike-based processing in the brain, spiking neural networks (SNNs) are developed and act as a promising candidate for the new generation of artificial neural networks that aim to produce efficient cognitions as the brain. Due to the complex dynamics and nonlinearity of SNNs, designing efficient learning algorithms has remained a major difficulty, which attracts great research attention. Most existing ones focus on the adjustment of synaptic weights. However, other components, such as synaptic delays, are found to be adaptive and important in modulating neural behavior. How could plasticity on different components cooperate to improve the learning of SNNs remains as an interesting question. Advancing our previous multispike learning, we propose a new joint weight-delay plasticity rule, named TDP-DL, in this article. Plastic delays are integrated into the learning framework, and as a result, the performance of multispike learning is significantly improved. Simulation results highlight the effectiveness and efficiency of our TDP-DL rule compared to baseline ones. Moreover, we reveal the underlying principle of how synaptic weights and delays cooperate with each other through a synthetic task of interval selectivity and show that plastic delays can enhance the selectivity and flexibility of neurons by shifting information across time. Due to this capability, useful information distributed away in the time domain can be effectively integrated for a better accuracy performance, as highlighted in our generalization tasks of the image, speech, and event-based object recognitions. Our work is thus valuable and significant to improve the performance of spike-based neuromorphic computing.

Human-Level Control Through Directly Trained Deep Spiking Q-Networks

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), that is, the reinforcement learning (RL) based on SNNs, is still in its preliminary stage due to the binary output and the nondifferentiable property of the spiking function. To address these issues, we propose a deep spiking Q -network (DSQN) in this article. Specifically, we propose a directly trained DSRL 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 DSQN. 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, generalization 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.

Deep Spike Learning With Local Classifiers

Backpropagation has been successfully generalized to optimize deep spiking neural networks (SNNs), where, nevertheless, gradients need to be propagated back through all layers, resulting in a massive consumption of computing resources and an obstacle to the parallelization of training. A biologically motivated scheme of local learning provides an alternative to efficiently train deep networks but often suffers a low performance of accuracy on practical tasks. Thus, how to train deep SNNs with the local learning scheme to achieve both efficient and accurate performance still remains an important challenge. In this study, we focus on a supervised local learning scheme where each layer is independently optimized with an auxiliary classifier. Accordingly, we first propose a spike-based efficient local learning rule by only considering the direct dependencies in the current time. We then propose two variants that additionally incorporate temporal dependencies through a backward and forward process, respectively. The effectiveness and performance of our proposed methods are extensively evaluated with six mainstream datasets. Experimental results show that our methods can successfully scale up to large networks and substantially outperform the spike-based local learning baselines on all studied benchmarks. Our results also reveal that gradients with temporal dependencies are essential for high performance on temporal tasks, while they have negligible effects on rate-based tasks. Our work is significant as it brings the performance of spike-based local learning to a new level with the computational benefits being retained.

Self-Adaptive Multicompartment: A Unified Self-Adaptive Multicompartmental Spiking Neuron Model for Learning With Working Memory

Working memory is a fundamental feature of biological brains for perception, cognition, and learning. In addition, learning with working memory, which has been show in conventional artificial intelligence systems through recurrent neural networks, is instrumental to advanced cognitive intelligence. However, it is hard to endow a simple neuron model with working memory, and to understand the biological mechanisms that have resulted in such a powerful ability at the neuronal level. This article presents a novel self-adaptive multicompartment spiking neuron model, referred to as SAM, for spike-based learning with working memory. SAM integrates four major biological principles including sparse coding, dendritic non-linearity, intrinsic self-adaptive dynamics, and spike-driven learning. We first describe SAM’s design and explore the impacts of critical parameters on its biological dynamics. We then use SAM to build spiking networks to accomplish several different tasks including supervised learning of the MNIST dataset using sequential spatiotemporal encoding, noisy spike pattern classification, sparse coding during pattern classification, spatiotemporal feature detection, meta-learning with working memory applied to a navigation task and the MNIST classification task, and working memory for spatiotemporal learning. Our experimental results highlight the energy efficiency and robustness of SAM in these wide range of challenging tasks. The effects of SAM model variations on its working memory are also explored, hoping to offer insight into the biological mechanisms underlying working memory in the brain. The SAM model is the first attempt to integrate the capabilities of spike-driven learning and working memory in a unified single neuron with multiple timescale dynamics. The competitive performance of SAM could potentially contribute to the development of efficient adaptive neuromorphic computing systems for various applications from robotics to edge computing.

ALSA: Associative Learning Based Supervised Learning Algorithm for SNN

Spiking neural network (SNN) is considered to be the brain-like model that best conforms to the biological mechanism of the brain. Due to the non-differentiability of the spike, the training method of SNNs is still incomplete. This paper proposes a supervised learning method for SNNs based on associative learning: ALSA. The method is based on the associative learning mechanism, and its realization is similar to the animal conditioned reflex process, with strong physiological plausibility and rationality. This method uses improved spike-timing-dependent plasticity (STDP) rules, combined with a teacher layer to induct spikes of neurons, to strengthen synaptic connections between input spike patterns and specified output neurons, and weaken synaptic connections between unrelated patterns and unrelated output neurons. Based on ALSA, this paper also completed the supervised learning classification tasks of the IRIS dataset and the MNIST dataset, and achieved 95.7 and 91.58% recognition accuracy, respectively, which fully proves that ALSA is a feasible SNNs supervised learning method. The innovation of this paper is to establish a biological plausible supervised learning method for SNNs, which is based on the STDP learning rules and the associative learning mechanism that exists widely in animal training.

Few-Shot Learning in Spiking Neural Networks by Multi-Timescale Optimization

Learning new concepts rapidly from a few examples is an open issue in spike-based machine learning. This few-shot learning imposes substantial challenges to the current learning methodologies of spiking neuron networks (SNNs) due to the lack of task-related priori knowledge. The recent learning-to-learn (L2L) approach allows SNNs to acquire priori knowledge through example-level learning and task-level optimization. However, an existing L2L-based framework does not target the neural dynamics (i.e., neuronal and synaptic parameter changes) on different timescales. This diversity of temporal dynamics is an important attribute in spike-based learning, which facilitates the networks to rapidly acquire knowledge from very few examples and gradually integrate this knowledge. In this work, we consider the neural dynamics on various timescales and provide a multi-timescale optimization (MTSO) framework for SNNs. This framework introduces an adaptive-gated LSTM to accommodate two different timescales of neural dynamics: short-term learning and long-term evolution. Short-term learning is a fast knowledge acquisition process achieved by a novel surrogate gradient online learning (SGOL) algorithm, where the LSTM guides gradient updating of SNN on a short timescale through an adaptive learning rate and weight decay gating. The long-term evolution aims to slowly integrate acquired knowledge and form, which can be achieved by optimizing the LSTM guidance process to tune SNN parameters on a long timescale. Experimental results demonstrate that the collaborative optimization of multi-timescale neural dynamics can make SNNs achieve promising performance for the few-shot learning tasks.