Deep learning

Video Deep learning

Awesome Recurrent Neural Networks
Awesome Deep Vision
Deep Learning Papers Reading Roadmap
Oxford Deep NLP 2017 course
Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation
Keras Deep Learning library for Python. Runs on TensorFlow, Theano or CNTK
OpenCL Caffe
Caffe: a fast open framework for deep learning
Caffe is a deep learning framework made with expression, speed, and modularity in mind
Forward and Backward
Caffe Tutorial
Coriander Build NVIDIA® CUDA™ code for OpenCL™ 1.2 devices
The LLVM Compiler Infrastructure
Thrust is a parallel algorithms library which resembles the C++ Standard Template Library (STL).
CUDA-on-CL: a compiler and runtime for running NVIDIA® CUDA™ C++11 applications on OpenCL™ 1.2 Devices
Yann LeCun
The Jupyter Notebook
Анализ временных рядов с помощью Python
Визуализация данных c Python
Time Series Analysis (TSA) in Python — Linear Models to GARCH
Keras: The Python Deep Learning library
Keras Models
A Peek at Trends in Machine Learning
Keras Библиотеки для глубокого обучения
Installing TensorFlow for Java
Библиотека глубокого обучения Tensorflow
TensorFlow. Библиотека машинного обучения от Google
TensorFlow Tutorial and Examples for beginners
Data mining: Инструментарий — Theano
Нейронные сети: практическое применение
Введение в машинное обучение с помощью Python и Scikit-Learn
The Open Images dataset
Deep Learning Datasets
ImageNet is an image database
Image Databases
FMA: A Dataset For Music Analysis
The CIFAR-10 dataset
CIFAR-10 — Object Recognition in Images
CIFAR-10 — Object Recognition in Images
Alex’s CIFAR-10 tutorial, Caffe style
92.45% on CIFAR-10 in Torch


CUDA Toolkit
Deep Learning Software
Accelerated Computing Toolkit
Coriander Build NVIDIA® CUDA™ code for OpenCL™ 1.2 devices
tf-coriander OpenCL 1.2 implementation for Tensorflow
Deep Learning Tutorial notes and code
Deep Learning Tutorials
A list of popular github projects related to deep learning
Deep learning library featuring a higher-level API for TensorFlow.

Caffe installation
Easily craft fast Neural Networks on iOS! Use TensorFlow models
Apple Build more intelligent apps with machine learning
Apple Integrating a Core ML Model into Your App
coremltools 0.3.0 Community Tools for CoreML. Core ML is an Apple framework which allows developers to simply and easily integrate machine learning (ML) models into apps running on Apple devices

Python Numpy Tutorial
numpy 1.13.0
Obtaining NumPy & SciPy libraries
Scipy Lecture Notes One document to learn numerics, science, and data with Python
Learn Python Programming
Python Programming Examples
Учите Питон
ROCm, a New Era in Open GPU Computing
ROCm — Open Source Platform for HPC and Ultrascale GPU Computing
yusugomori DeepLearning


Базовые принципы машинного обучения на примере линейной регрессии
Искусственный интеллект Путина довел Америку до истерики


These datasets can be used for benchmarking deep learning algorithms:

Music Datasets

Natural Images

Artificial Datasets




Recommendation Systems

  • MovieLens: Two datasets available from The first dataset has 100,000 ratings for 1682 movies by 943 users, subdivided into five disjoint subsets. The second dataset has about 1 million ratings for 3900 movies by 6040 users.
  • Jester: This dataset contains 4.1 million continuous ratings (-10.00 to +10.00) of 100 jokes from 73,421 users.
  • Netflix Prize: Netflix released an anonymised version of their movie rating dataset; it consists of 100 million ratings, done by 480,000 users who have rated between 1 and all of the 17,770 movies.
  • Book-Crossing dataset: This dataset is from the Book-Crossing community, and contains 278,858 users providing 1,149,780 ratings about 271,379 books.



Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
Нейросеть DeepCoder учится программировать, заимствуя код у других программ
DeepCoder: Learning to Write Programs
Искуственный интеллект научился писать код
Our mission at DeepCode is to change the way we create programs by using powerful artificial intelligence and machine learning methods.

TensorBoard: Visualizing Learning

GitHub TensorFlow
Applied Deep Learning for Computer Vision with Torch

Deep learning with dynamic computation graphs in TensorFlow Fold

Deep learning GitHub
AMD представила Radeon Instinct – в фокусе машинное обучение
Deep learning for computational biology

Leave a Reply

Ваш e-mail не будет опубликован. Обязательные поля помечены *