RNN的输出 [英] Output for an RNN

问题描述

我正在参加由多伦多大学的Geoffrey Hinton主持的Coursera课程机器学习神经网络" ，第7周有一个测验问题，我的答案与正确的答案有所不同.

I'm taking the Coursera course Neural Networks for Machine Learning hosted by Geoffrey Hinton from the University of Toronto and there is a quiz question in week 7 for which my answer differs from the right one.

问题如下:

一个问题是，如果Whh权重为负并且logistic h单位给出的值介于0和1之间，那么我应该如何获得0到1之间的概率.

One question is, how should I get a probability between 0 and 1 if the Whh weight is negative and the logistic h unit gives values between 0 and 1. Given the above, their linear combination will allways be negative.

第二个问题是我们是否还必须使用反向传播才能获得正确的答案?

A second question would be if we also have to use backpropagation in order to get the right answer?

我开始解决此问题的方法如下:

The way I've started to tackle this question is the following:

h0 = 1/( 1 + exp(- (Whh * hbias + Wxh*x0)) )

h1 = 1/( 1 + exp(- (Whh * h0 + Wxh*x1)))

y1 = Why * h1

我的哪些假设不正确?

关于， 克里斯蒂安(Cristian)

Regards, Cristian

推荐答案

尝试一下.

h0 = sigmoid(x0*Wxh + hbias)
h1 = sigmoid(x1*Wxh + Whh*h0 + hbias)
y1 = h1*Why

这篇关于RNN的输出的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！