c语言实现神经网络MNIST,MNIST数据集的神经网络实现，用普通的C语言编写

MNIST Neural Network in C

This source code seeks to replicate the MNIST For ML Beginners tutorial from the Tensorflow website using plain C code.

The task is to recognise digits, such as the ones below, as accurately as possible.

Contents

mnist.c: Glue code that runs the algorithm steps and reports algorithm accuracy

mnist_file.c: Retrieves images and labels from the MNIST dataset

neural_network.c: Implements training and prediction routines for a simple neural network

Usage

make

./mnist

Description

The neural network implemented has one output layer and no hidden layers. Softmax activation is used, and this ensures that the output activations form a probability vector corresponding to each label. The cross entropy is used as a loss function.

The algorithm reaches an accuracy of around 92% over 1000 steps.

Expected Output

Step 0000Average Loss: 4.36Accuracy: 0.152

Step 0001Average Loss: 3.42Accuracy: 0.188

Step 0002Average Loss: 2.97Accuracy: 0.298

Step 0003Average Loss: 2.53Accuracy: 0.319

Step 0004Average Loss: 2.19Accuracy: 0.412

Step 0005Average Loss: 2.08Accuracy: 0.437

Step 0006Average Loss: 1.73Accuracy: 0.468

Step 0007Average Loss: 1.51Accuracy: 0.447

Step 0008Average Loss: 1.57Accuracy: 0.496

Step 0009Average Loss: 1.45Accuracy: 0.516

Step 0010Average Loss: 1.78Accuracy: 0.559

...