论文标题
在皮质微电路中局部监督的生物学上合理的神经网络
A biologically plausible neural network for local supervision in cortical microcircuits
论文作者
论文摘要
反向传播算法是训练人工神经网络的宝贵工具；但是，由于重量共享要求，它不能提供大脑功能的合理模型。在这里，在两层网络的上下文中，我们得出了一种用于训练神经网络的算法，该算法通过不需要明确的错误计算和反向传播来避免此问题。此外，我们的算法映射到与皮质的连通性结构和学习规则相似的神经网络上。我们发现，我们的算法在许多数据集上的经验上与反向推销相当。
The backpropagation algorithm is an invaluable tool for training artificial neural networks; however, because of a weight sharing requirement, it does not provide a plausible model of brain function. Here, in the context of a two-layer network, we derive an algorithm for training a neural network which avoids this problem by not requiring explicit error computation and backpropagation. Furthermore, our algorithm maps onto a neural network that bears a remarkable resemblance to the connectivity structure and learning rules of the cortex. We find that our algorithm empirically performs comparably to backprop on a number of datasets.
