0

我有一个用于神经网络的 MATLAB 代码,训练网络大约需要 3 分钟。(它训练大约 85 个文件)。当我使用它时,profile viewer它说trainlm有一个自我时间 143.166s,其中 83.3% 的时间来自dWB = -(jj+ii*mu) \ je;

有没有办法让它更快?我应该使用数据分箱吗?

提前致谢!

4

2 回答 2

1

That one line is a solution of a linear system of equations. The limit here is the number of unknowns, so the size of your network which defines the number of unknowns.

No, you cannot really reduce that time easily, unless you are willing to reduce the number of unknowns, or buy/find a faster computer.

于 2013-07-26T13:37:51.010 回答
0

您是否已经检查过是否可以以某种方式使用parfor并行计算工具箱或一般的并行计算工具箱来并行化您的代码?

于 2013-07-26T12:19:27.887 回答