GitHub - jperla/neural: neural networks, sparse encoders, and recursive auto encoder sin python

jperla / neural Public

Notifications You must be signed in to change notification settings
Fork 50
Star 99

neural networks, sparse encoders, and recursive auto encoder sin python

99 stars 50 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 35 Commits
deep		deep
pca		pca
rae		rae
selftaught		selftaught
softmax		softmax
tests		tests
.gitignore		.gitignore
README		README
display_network.py		display_network.py
neurolib.py		neurolib.py
numerical_gradient.py		numerical_gradient.py
sample_images.py		sample_images.py
sparse_autoencoder.py		sparse_autoencoder.py
train_sparse_autoencoder_on_matlab_images.py		train_sparse_autoencoder_on_matlab_images.py
train_sparse_autoencoder_on_mnist.py		train_sparse_autoencoder_on_mnist.py

Repository files navigation

This is a rewrite of the tutorial about unsupervised feature learning and deep learning in Python using numpy and scipy.

Tutorial: http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial

I use numpy for matrices, and scipy.optimize package for the L-BFGS minimization algorithm.

Deep learning learns low and high-level features from large amounts of unlabeled data, improving classification on different, labeled, datasets.  Deep learning can achieve an accuracy of 98% on the MNIST dataset.