机器学习相关问题汇集

1. What do the fully connected layers do in CNNs?
   http://stats.stackexchange.com/questions/182102/what-do-the-fully-connected-layers-do-in-cnns/182122#182122
   I understand the convolutional and pooling layers, but I cannot see the reason for a fully connected layer in CNNs. Why isn’t the previous layer directly connected to the output layer?

The output from the convolutional layers represents high-level features in the data. While that output could be flattened and connected to the output layer, adding a fully-connected layer is a (usually) cheap way of learning non-linear combinations of these features.

Essentially the convolutional layers are providing a meaningful, low-dimensional, and somewhat invariant feature space, and the fully-connected layer is learning a (possibly non-linear) function in that space.