In recent years, there has been an intense debate about how learning in biological neural networks (BNNs) differs from learning in artificial neural networks. It is often argued that the updating of connections in the brain relies only on local information, and therefore a stochastic gradient-descent type optimization method cannot be used. In this paper, we study a stochastic model for supervised learning in BNNs. We show that a (continuous) gradient step occurs approximately when each learning opportunity is processed by many local updates. This result suggests that stochastic gradient descent may indeed play a role in optimizing BNNs.

翻译：近年来，关于生物神经网络（BNNs）中的学习与人工神经网络中的学习有何差异引发了激烈争论。通常认为，大脑中连接的更新仅依赖局部信息，因此随机梯度下降类优化方法无法直接应用。本文针对BNN中的监督学习过程建立了一个随机模型，并证明：当每个学习机会通过多次局部更新进行处理时，会近似产生（连续）梯度步长。这一结果表明，随机梯度下降或许确实在优化BNNs中发挥作用。