Exercise:Softmax Regression
From Ufldl
(→Step 4: Learning parameters) |
(→Step 4: Learning parameters) |
||
Line 99: | Line 99: | ||
Factoring <tt>softmaxTrain</tt> out as a function means that you will be able to easily reuse it to train softmax models on other data sets in the future by invoking the function with different parameters. | Factoring <tt>softmaxTrain</tt> out as a function means that you will be able to easily reuse it to train softmax models on other data sets in the future by invoking the function with different parameters. | ||
- | Use the following | + | Use the following parameter when training your softmax classifier: |
lambda = 1e-3 | lambda = 1e-3 |