Multilayer Perceptron — DeepLearning 0.1 documentation

Note This section assumes the reader has already read through Classifying MNIST digits using Logistic Regression. Additionally, it uses the following new Theano functions and concepts: T.tanh, shared variables, basic arithmetic ops, T.grad, L1 and L2 regularization, floatX. If you intend to run the code on GPU also read GPU. The next architecture we are going to present using Theano is the single-

[aidiary]

MNISTの分類の例あり