Horizontally layering LSTM cells
我对整个神经网络领域还是很陌生,我刚刚学习了一些关于 LSTM 单元的教程,特别是 tensorflow。
在教程中,他们有一个对象 tf.nn.rnn_cell.MultiRNNCell,据我了解,它是 LSTM 单元的垂直分层,类似于分层卷积网络。但是,我找不到任何关于水平 LSTM 单元的信息,其中一个单元的输出是另一个单元的输入。
我知道因为细胞是循环的,所以它们不需要这样做,但我只是想看看这是否可能。
干杯!
However, I couldn’t find anything about horizontal LSTM cells, in which the output of one cell is the input of another.
这是重复的定义。所有 RNN 都这样做。
来源:https://www.codenong.com/38490811/
微信公众号
手机浏览(小程序)
Warning: get_headers(): SSL operation failed with code 1. OpenSSL Error messages:
error:14090086:SSL routines:ssl3_get_server_certificate:certificate verify failed in
/mydata/web/wwwshanhubei/web/wp-content/themes/shanhuke/single.php on line
57
Warning: get_headers(): Failed to enable crypto in
/mydata/web/wwwshanhubei/web/wp-content/themes/shanhuke/single.php on line
57
Warning: get_headers(https://static.shanhubei.com/qrcode/qrcode_viewid_10215.jpg): failed to open stream: operation failed in
/mydata/web/wwwshanhubei/web/wp-content/themes/shanhuke/single.php on line
57