论文标题
对背部传播及其在多层感知的替代方案的比较研究
A comparative study of back propagation and its alternatives on multilayer perceptrons
论文作者
论文摘要
用于训练前馈神经网络的后通过的事实算法是反向传播（BP）。几乎所有地方的可微分激活功能的使用使通过深神经网络层次向后传播梯度的梯度使其有效。但是，近年来，反向传播的替代方案有很多研究。该分析主要集中在达到多层感知器（MLP）和卷积神经网络（CNN）中的最先进精度。在本文中，我们分析了MLP中预测和神经元的稳定性和相似性，并提出了其中一种算法的新变化。
The de facto algorithm for training the back pass of a feedforward neural network is backpropagation (BP). The use of almost-everywhere differentiable activation functions made it efficient and effective to propagate the gradient backwards through layers of deep neural networks. However, in recent years, there has been much research in alternatives to backpropagation. This analysis has largely focused on reaching state-of-the-art accuracy in multilayer perceptrons (MLPs) and convolutional neural networks (CNNs). In this paper, we analyze the stability and similarity of predictions and neurons in MLPs and propose a new variation of one of the algorithms.
