Schmidgall Samuel, Ashkanazy Julia, Lawson Wallace, Hays Joe
U.S. Naval Research Laboratory, Washington, DC, United States.
Front Neurorobot. 2021 Sep 22;15:629210. doi: 10.3389/fnbot.2021.629210. eCollection 2021.
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.
在发放脉冲的神经元之间发生的突触效能适应性变化，已被证明在生物神经网络的学习中起着关键作用。尽管有这种灵感来源，但许多使用脉冲神经网络（SNN）的以学习为重点的应用仍保留静态突触连接，从而在初始训练期之后阻止了进一步学习。在此，我们引入一个框架，通过梯度下降同时学习SNN中潜在的固定权重以及控制突触可塑性和神经调节突触可塑性动态的规则。我们进一步在一系列具有挑战性的基准测试中展示了该框架的能力，学习了包括BCM、奥贾规则及其各自的神经调节变体集在内的几种可塑性规则的参数。实验结果表明，增强了可微可塑性的SNN足以解决传统SNN无法解决的一组具有挑战性的时间学习任务，即使在存在大量噪声的情况下也是如此。这些网络还被证明能够在高维机器人学习任务中产生运动，在初始训练期未见过的新条件下，性能仅有近乎最小的下降。
