神经网络 调节参数

cs231a: assignment2

What's wrong? Looking at the visualizations above, we see that the loss is decreasing more or less linearly, which seems to suggest that the learning rate may be too low. Moreover, there is no gap between training and validation accuracy, suggesting that the model we used has low capacity, and that we should increase its size. On the other hand, with a very large model we expect to see more overfitting, which would manifest itself as a very large gap between the training and validation accuracy.

Turing。Turing the hyperparameters and developing intuition for how they affect the final performance is a large part of Neural Networks. So you should experiment with different values of the various hyperparameters, including hidden layer size, learning rate, number of training epochs, and regularization strength. You might also consider tuning the momentum and learning rate decay parameters.

PCA to reduce dimensionality, adding dropout, or adding features to the solver. 

最终结果。