halisyilboga1 Goto Github PK

adnn

Javascript neural networks on top of general scalar/tensor reverse-mode automatic differentiation.

cadl

Course materials/Homework materials for the FREE MOOC course on "Creative Applications of Deep Learning w/ Tensorflow" #CADL

chainedgp

Repository for Chained Gaussian Processes

char-rnn-tensorflow

Multi-layer Recurrent Neural Networks (LSTM, RNN) for character-level language models in Python using Tensorflow

convnetjs

Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.

cs231n-assignments

deep-residual-networks

Deep Residual Learning for Image Recognition

deepjazz

Deep learning driven jazz generation using Keras & Theano!

deeppr

License Plate Recognition via Deep Learning

dl-docker

An all-in-one Docker image for deep learning. Contains all the popular DL frameworks (TensorFlow, Theano, Torch, Caffe, etc.)

docker

Docker files

halisyilboga.github.io

handong1587.github.io

kaldi

This is now the official location of the Kaldi project.

keras-language-modeling

Some language modeling tools for Keras deep learning framework

mldb

MLDB is the Machine Learning Database

movienetwork

mxnet

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Go, Javascript and more

neural-style

Torch implementation of neural style algorithm

neuralstyle-music

Music visualizer using neural style

neuraltalk

NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.

ntm-one-shot

One-shot Learning with Memory-Augmented Neural Networks

openalpr

Automatic License Plate Recognition library

poetry-generator

A Python3 based Backus-Naur poetry generator

rnnexp

separable-sss

Separable Subsurface Scattering is a technique that allows to efficiently perform subsurface scattering calculations in screen space in just two passes.

tensorflow-ipythonnotebook

tensorflow with IPythonNotebook

wide-residual-networks

95.8% and 80% on CIFAR-10 and CIFAR-100