Bohnstingl Thomas, Wozniak Stanislaw, Pantazi Angeliki, Eleftheriou Evangelos
IEEE Trans Neural Netw Learn Syst. 2023 Nov;34(11):8894-8908. doi: 10.1109/TNNLS.2022.3153985. Epub 2023 Oct 27.
Biological neural networks are equipped with an inherent capability to continuously adapt through online learning. This aspect remains in stark contrast to learning with error backpropagation through time (BPTT) that involves offline computation of the gradients due to the need to unroll the network through time. Here, we present an alternative online learning algorithm ic framework for deep recurrent neural networks (RNNs) and spiking neural networks (SNNs), called online spatio-temporal learning (OSTL). It is based on insights from biology and proposes the clear separation of spatial and temporal gradient components. For shallow SNNs, OSTL is gradient equivalent to BPTT enabling for the first time online training of SNNs with BPTT-equivalent gradients. In addition, the proposed formulation unveils a class of SNN architectures trainable online at low time complexity. Moreover, we extend OSTL to a generic form, applicable to a wide range of network architectures, including networks comprising long short-term memory (LSTM) and gated recurrent units (GRUs). We demonstrate the operation of our algorithm ic framework on various tasks from language modeling to speech recognition and obtain results on par with the BPTT baselines.
生物神经网络具备通过在线学习持续适应的内在能力。这一点与通过时间反向传播误差（BPTT）学习形成鲜明对比，BPTT由于需要随时间展开网络而涉及梯度的离线计算。在此，我们提出一种用于深度循环神经网络（RNN）和脉冲神经网络（SNN）的在线学习算法框架，称为在线时空学习（OSTL）。它基于生物学见解，提出将空间和时间梯度分量明确分离。对于浅层SNN，OSTL在梯度上等同于BPTT，首次实现了具有BPTT等效梯度的SNN在线训练。此外，所提出的公式揭示了一类可在低时间复杂度下在线训练的SNN架构。而且，我们将OSTL扩展为通用形式，适用于广泛的网络架构，包括包含长短期记忆（LSTM）和门控循环单元（GRU）的网络。我们在从语言建模到语音识别等各种任务上展示了我们算法框架的运行情况，并获得了与BPTT基线相当的结果。
