Department of Physiology, University of Toronto, Toronto, Ontario M5S 1A8, Canada.
Neural Comput. 2012 Jun;24(6):1487-518. doi: 10.1162/NECO_a_00277. Epub 2012 Feb 24.
Many neural control systems are at least roughly optimized, but how is optimal control learned? There are algorithms for this purpose, but in their current forms, they are not suited for biological neural networks because they rely on a type of communication that is not available in the brain, namely, weight transport-transmitting the strengths, or "weights," of individual synapses to other synapses and neurons. Here we show how optimal control can be learned without weight transport. Our method involves a set of simple mechanisms that can compensate for the absence of weight transport in the brain and so may be useful for neural computation generally.
许多神经控制系统至少是大致优化的，但最优控制是如何学习的呢？为此有一些算法，但就目前形式而言，它们并不适用于生物神经网络，因为它们依赖于一种大脑中没有的通讯方式，即权重传输——将单个突触的强度或“权重”传输到其他突触和神经元。在这里，我们展示了如何在没有权重传输的情况下学习最优控制。我们的方法涉及一组简单的机制，可以弥补大脑中权重传输的缺失，因此可能对一般的神经计算有用。
