Data_Sheet_1_SpikePropamine: Differentiable Plasticity in Spiking Neural Networks.pdf

The adaptive changes in synaptic efficacy that occur between spiking neurons have been demonstrated to play a critical role in learning for biological neural networks. Despite this source of inspiration, many learning focused applications using Spiking Neural Networks (SNNs) retain static synaptic connections, preventing additional learning after the initial training period. Here, we introduce a framework for simultaneously learning the underlying fixed-weights and the rules governing the dynamics of synaptic plasticity and neuromodulated synaptic plasticity in SNNs through gradient descent. We further demonstrate the capabilities of this framework on a series of challenging benchmarks, learning the parameters of several plasticity rules including BCM, Oja's, and their respective set of neuromodulatory variants. The experimental results display that SNNs augmented with differentiable plasticity are sufficient for solving a set of challenging temporal learning tasks that a traditional SNN fails to solve, even in the presence of significant noise. These networks are also shown to be capable of producing locomotion on a high-dimensional robotic learning task, where near-minimal degradation in performance is observed in the presence of novel conditions not seen during the initial training period.

脉冲神经元（spiking neuron）之间突触效能（synaptic efficacy）的适应性变化，已被证实对生物神经网络的学习过程发挥着至关重要的作用。尽管这一生物学启发思路为研究提供了重要借鉴，但当前多数聚焦学习任务的脉冲神经网络（Spiking Neural Networks, SNN）应用仍采用静态突触连接，导致初始训练阶段结束后无法开展额外学习。本研究提出一种框架，可通过梯度下降法，同时学习脉冲神经网络中的底层固定权重，以及调控突触可塑性（synaptic plasticity）与神经调制型突触可塑性（neuromodulated synaptic plasticity）动态变化的规则。我们进一步在一系列具有挑战性的基准测试任务中验证了该框架的性能，完成了包括BCM规则、Oja规则及其各自的神经调制变体在内的多种可塑性规则的参数学习。实验结果表明，搭载可微可塑性（differentiable plasticity）机制的脉冲神经网络，足以解决传统脉冲神经网络无法完成的一系列具有挑战性的时序学习任务，即便在存在显著噪声的场景下亦是如此。此外，该类网络还可在高维机器人学习任务中实现运动控制，且在初始训练阶段未见过的全新场景下，其性能仅出现近乎可忽略的衰减。