part of a series on |
artificial intelligence (ai) |
---|
![]() |
deep learning (tsz. deep learnings)
A deep learning egy dinamikusan fejlődő terület, amely jelentős hatással van a mesterséges intelligencia és gépi tanulás világára. Az összetett minták és összefüggések észlelésére és az önálló tanulásra való képessége miatt a mélytanulás széleskörű alkalmazásokat talál számos iparágban, a számítógépes látástól kezdve a természetes nyelvfeldolgozásig. Bár a mélytanulás számos előnnyel jár, a hozzá szükséges erőforrások és az adatigény miatt a kihívások is jelentősek.
Software | Creator | Initial release | Software license | Open source | Platform | Written in | Interface | OpenMP support | OpenCL support | CUDA support | ROCm support | Automatic differentiation | Has pretrained models | Recurrent nets | Convolutional nets | RBM/DBNs | Parallel execution (multi node) | Actively developed |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
BigDL | Jason Dai (Intel) | 2016 | free | yes | Apache Spark | Scala | Scala, Python | no | no | yes | yes | yes | yes | |||||
Caffe | Berkeley Vision and Learning Center | 2013 | BSD-lic | yes | Linux, macOS, Windows | C++ | Python, MATLAB, C++ | yes | Under development | yes | no | yes | yes | yes | yes | no | ? | no |
Chainer | Preferred Networks | 2015 | BSD-lic | yes | Linux, macOS | Python | Python | no | no | yes | no | yes | yes | yes | yes | no | yes | no |
Deeplearning4j | Skymind engineering team; Deeplearning4j community; originally Adam Gibson | 2014 | free | yes | Linux, macOS, Windows, Android (Cross-platform) | C++, Java | Java, Scala, Clojure, Python (Keras), Kotlin | yes | no | yes | no | yes | yes | yes | yes | yes | yes | yes |
Dlib | Davis King | 2002 | free | yes | Cross-platform | C++ | C++, Python | yes | no | yes | no | yes | yes | no | yes | yes | yes | yes |
Flux | Mike Innes | 2017 | free | yes | Linux, MacOS, Windows (Cross-platform) | Julia | Julia | yes | no | yes | yes | yes | yes | no | yes | yes | ||
Intel Data Analytics Acceleration Library | Intel | 2015 | free | yes | Linux, macOS, Windows on Intel CPU | C++, Python, Java | C++, Python, Java | yes | no | no | no | yes | no | yes | yes | yes | ||
Intel Math Kernel Library 2017 | Intel | 2017 | Proprietary | no | Linux, macOS, Windows on Intel CPU | C/C++, DPC++, Fortran | C | yes | no | no | no | yes | no | yes | yes | no | yes | |
Google JAX | 2018 | free | yes | Linux, macOS, Windows | Python | Python | ? | no | yes | no | yes | yes | ||||||
Keras | François Chollet | 2015 | free | yes | Linux, macOS, Windows | Python | Python, R | ? | ? | yes | no | yes | yes | yes | yes | no | yes | yes |
MATLAB + Deep Learning Toolbox (formally Neural Network Toolbox) | MathWorks | 1992 | Proprietary | no | Linux, macOS, Windows | C, C++, Java, MATLAB | MATLAB | no | no | yes | no | yes | yes | yes | yes | yes | yes | yes |
Microsoft Cognitive Toolkit (CNTK) | Microsoft Research | 2016 | free | yes | Windows, Linux | C++ | Python (Keras), C++, Command line, | yes | no | yes | no | yes | yes | yes | yes | no | yes | no |
ML.NET | Microsoft | 2018 | free | yes | Windows, Linux, macOS | C#, C++ | C#, F# | yes | ||||||||||
Apache MXNet | Apache Software Foundation | 2015 | free | yes | Linux, macOS, Windows, | Small C++ core library | C++, Python, Julia, MATLAB, JavaScript, Go, R, Scala, Perl, Clojure | yes | no | yes | no | yes | yes | yes | yes | yes | yes | no |
Neural Designer | Artelnics | 2014 | Proprietary | no | Linux, macOS, Windows | C++ | Graphical user interface | yes | no | yes | no | no | no | no | no | no | yes | yes |
OpenNN | Artelnics | 2003 | LGPL | yes | Cross-platform | C++ | C++ | yes | no | yes | no | ? | ? | no | no | no | ? | yes |
PlaidML | Vertex.AI, Intel | 2017 | free | yes | Linux, macOS, Windows | Python, C++, OpenCL | Python, C++ | ? | yes | no | no | yes | yes | yes | yes | yes | yes | |
PyTorch | Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan (Facebook) | 2016 | BSD-lic | yes | Linux, macOS, Windows, Android | Python, C, C++, CUDA | Python, C++, Julia, R | yes | ? | yes | yes | yes | yes | yes | yes | yes | yes | yes |
Apache SINGA | Apache Software Foundation | 2015 | free | yes | Linux, macOS, Windows | C++ | Python, C++, Java | no | ? | yes | no | ? | yes | yes | yes | yes | yes | yes |
TensorFlow | Google Brain | 2015 | free | yes | Linux, macOS, Windows, | C++, Python, CUDA | Python (Keras), C/C++, Java, Go, JavaScript, R, | no | ? | yes | yes | yes | yes | yes | yes | yes | yes | yes |
Theano | Université de Montréal | 2007 | BSD-lic | yes | Cross-platform | Python | Python (Keras) | yes | Under development | yes | no | yes | Through Lasagne's model zoo | yes | yes | yes | yes | no |
Torch | Ronan Collobert, Koray Kavukcuoglu, Clement Farabet | 2002 | BSD-lic | yes | Linux, macOS, Windows, | C, Lua | Lua, LuaJIT, | yes | Third party implementations | yes | no | Through Twitter's Autograd | yes | yes | yes | yes | yes | no |
Wolfram Mathematica 10 | Wolfram Research | 2014 | Proprietary | no | Windows, macOS, Linux, Cloud computing | C++, Wolfram Language, CUDA | Wolfram Language | yes | no | yes | no | yes | yes | yes | yes | yes | yes | yes |
Software | Creator | Initial release | Software license | Open source | Platform | Written in | Interface | OpenMP support | OpenCL support | CUDA support | ROCm support | Automatic differentiation | Has pretrained models | Recurrent nets | Convolutional nets | RBM/DBNs | Parallel execution (multi node) | Actively developed |