Convolution Neural Network on MATLAB

Contents

CIFAR_LeNet.m, an example of CIFAR-10 image classification with LeNet

MNIST_LeNet.m, an example of MNIST handwritten digits classification with LeNet

MNIST_ResNet.m, an example of MNIST handwritten digits classfication with deep residual net (incomplete)

Gravity_main.m, an example of Gravity signal detection

Datasets

The MNIST database of handwritten digits

http://yann.lecun.com/exdb/mnist/

The CIFAR-10 dataset

http://www.cs.toronto.edu/~kriz/cifar.html

Related papers

Gradient-based Learning Applied to Document Recognition

http://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf

Notes on Convolutional Neural Networks

https://pdfs.semanticscholar.org/714a/c6c7dbb83d69b8118e5138b3a50d8feb789b.pdf

Understanding the difficulty of training deep feedforward neural networks

http://machinelearning.wustl.edu/mlpapers/paper_files/AISTATS2010_GlorotB10.pdf

Batch normalization: Accelerating deep network training by reducing internal covariate shift

https://arxiv.org/pdf/1502.03167.pdf

Delving deep into rectifiers:Surpassing human-level performance on imagenet classification

https://arxiv.org/pdf/1502.01852.pdf

Imagenet classification with deep convolutional neural networks

http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf

Deep Residual Learning for Image Recognition

https://arxiv.org/pdf/1512.03385.pdf

On the Importance of Initialization and Momentum in Deep Learning

http://www.cs.toronto.edu/~fritz/absps/momentum.pdf