深度学习softmax识别数字

Introduction to MNIST Dataset The MNIST dataset is a dataset of handwritten digits, comprising 60 000 training examples and 10 000 test examples. The dataset can be downloaded from http://yann.lecun.com/exdb/mnist/. Usage The image and label data is stored in a binary format described on the website. For your convenience, we have provided two MATLAB helper functions for extracting the data. These functions are available at http://ufldl.stanford.edu/wiki/resources/mnistHelper.zip. As an example of how to use these functions, you can check example.m To do You need to design and implement your loss function and its derivatives with respect to its input. An example, softmax (cross-entropy) loss, has been provided for you. See 'loss/softmax.m'