Фреймворки, библиотеки программ и отдельные программы для глубинного обучения.
И ещё несколько вариантов (часть из них могут быть платными):
- adnn – Javascript neural networks
- Blocks – Theano framework for building and training neural networks
- Caffe2 – Deep learning framework built on Caffe, developed by Facebook in cooperation with NVIDIA, Qualcomm, Intel, Amazon, and Microsoft
- CaffeOnSpark – Scalable deep learning package running Caffe on Spark and Hadoop clusters with peer-to-peer communication
- CNNLab – Deep learning framework using GPU and FPGA-based accelerators
- ConvNetJS – Javascript library for training deep learning models entirely in a web browser
- Cortex – Theano-based deep learning toolbox for neuroimaging
- cuDNN – Optimized deep learning computation primitives implemented in CUDA
- CURRENNT – CUDA-accelerated toolkit for deep Long Short-Term Memory (LSTM) RNN architectures supporting large data sets not fitting into main memory.
- DeepCL – OpenCL library to train deep convolutional networks, with APIs for C++, Python and the command line
- deeplearn.js – Hardware-accelerated deep learning library for the web browser
- DeepLearningKit – Open source deep learning framework for iOS, OS X and tvOS
- DeepLearnToolbox – Matlab/Octave toolbox for deep learning (deprecated)
- DeepX – Software accelerator for deep learning execution aimed towards mobile devices
- deepy – Extensible deep learning framework based on Theano
- DSSTNE (Deep Scalable Sparse Tensor Network Engine) – Amazon developed library for building deep learning models
- Faster RNNLM (HS/NCE) toolkit – An rnnlm implementation for training on huge datasets and very large vocabularies and usage in real-world ASR and MT problems
- GNU Gneural Network – GNU package which implements a programmable neural network
- IDLF – Intel® Deep Learning Framework; supports OpenCL (deprecated)
- Intel Math Kernel Library (Intel MKL), library of optimized math routines, including optimized deep learning computation primitives
- Keras – Deep Learning library for Theano and TensorFlow
- Lasagne – Lightweight library to build and train neural networks in Theano
- Leaf – «The Hacker’s Machine Learning Engine»; supports OpenCL (official development suspended[4])
- LightNet – MATLAB-based environment for deep learning
- MatConvNet – CNNs for MATLAB
- MaTEx – Distributed TensorFlow with MPI by PNNL
- Mocha – Deep learning framework for Julia, inspired by Caffe
- neon – Nervana’s Python based Deep Learning framework
- Neural Network Toolbox – MATLAB toolbox for neural network creation, training and simulation
- PaddlePaddle – «PArallel Distributed Deep LEarning», deep learning platform
- Purine – Bi-graph based deep learning framework
- Pylearn2 – Machine learning library mainly built on top of Theano
- Pytorch — Python based implementation of Torch API, allows for dynamic graph construction
- scikit-neuralnetwork – Multi-layer perceptrons as a wrapper for Pylearn2
- sklearn-theano – Scikit-learn compatible tools using theano
- Tensor Builder – Lightweight extensible library for easy creation of deep neural networks using functions from «any Tensor-based library» (requires TensorFlow) through an API based on the Builder Pattern
- TensorGraph – Framework for building any models based on TensorFlow
- TensorFire – Neural networks framework for the web browser, accelerated by WebGL
- TF Learn (Scikit Flow) – Simplified interface for TensorFlow
- TF-Slim – High level library to define complex models in TensorFlow
- TFLearn – Deep learning library featuring a higher-level API for TensorFlow
- Theano-Lights – Deep learning research framework based on Theano
- tiny-dnn – Header only, dependency-free deep learning framework in C++11
- torchnet – Torch framework providing a set of abstractions aiming at encouraging code re-use as well as encouraging modular programming
- Veles – Distributed machine learning platform by Samsung