公开(公告)号：US20160162781A1

公开(公告)日：2016-06-09

申请号：US14907560

申请日：2014-07-25

申请人： ISIS INNOVATION LTD.

发明人： Timothy LILLICRAP ,  Colin Akerman ,  Douglas TWEED ,  Daniel COWNDEN

IPC分类号： G06N3/08 ,  G06N99/00

CPC分类号： G06N3/082 ,  G06N3/0454 ,  G06N20/00

摘要： A method of training a neural network having at least an input layer, an output layer and a hidden layer, and a weight matrix encoding connection weights between two of the layers, the method comprising the steps of (a) providing an input to the input layer, the input having an associated expected output, (b) receiving a generated output at the output layer, (c) generating an error vector from the difference between the generated output and expected output, (d) generating a change matrix, the change matrix being the product of a random weight matrix and the error vector, and (e) modifying the weight matrix in accordance with the change matrix.

摘要翻译： 一种训练具有至少输入层，输出层和隐藏层的神经网络的方法以及对两层之间的连接权重进行加权矩阵编码的方法，所述方法包括以下步骤：（a）向输入提供输入 所述输入具有相关联的预期输出，（b）在所述输出层处接收所生成的输出，（c）根据所生成的输出与预期输出之间的差产生误差向量，（d）生成改变矩阵，所述变化 矩阵是随机权重矩阵和误差向量的乘积，（e）根据变化矩阵修改权重矩阵。