RNN反向通过时间

时间:2018-05-18 11:22:10

标签: neural-network backpropagation rnn

我正在调查RNN,在阅读本文后,了解了Backrpop-through-time如何在RNN上运行: https://arxiv.org/pdf/1610.02583.pdf

但我对以下实现(来自cs231)感到困惑:

 for t in reversed(xrange(T)):
        dh_current = dh[t] + dh_prev
        dx_t, dh_prev, dWx_t, dWh_t, db_t = rnn_step_backward(dh_current, cache[t])
        dx[t] += dx_t
        dh0 = dh_prev
        dWx += dWx_t
        dWh += dWh_t
        db += db_t

为什么要总结dh [t]和dh_prev渐变, dh_current = dh [t] + dh_prev

完整源代码:https://github.com/williamchan/cs231-assignment3/blob/master/cs231n/rnn_layers.py

0 个答案:

没有答案