awesome-cpp-ml
My curated list of C++ (GPU) BLAS libraries and machine learning/reinforcement learning frameworks
https://github.com/bennylp/awesome-cpp-ml
Last synced: 1 day ago
JSON representation
-
Free/Open Source BLAS/Matrix Libraries
- ViennaCL - source linear algebra library for computations on many-core architectures (GPUs, MIC) and multi-core CPUs. The library is written in C++ and supports CUDA, OpenCL, and OpenMP (including switches at runtime).
- MAGMA
- CULA - accelerated linear algebra libraries utilizing the NVIDIA CUDA parallel computing architecture to dramatically improve the computation speed of sophisticated mathematics.
- Boost uBlas
- ViennaCL - source linear algebra library for computations on many-core architectures (GPUs, MIC) and multi-core CPUs. The library is written in C++ and supports CUDA, OpenCL, and OpenMP (including switches at runtime).
- MAGMA
- Boost uBlas
- NVidia cuBLAS - accelerated implementation of the standard basic linear algebra subroutines (BLAS).
- CULA - accelerated linear algebra libraries utilizing the NVIDIA CUDA parallel computing architecture to dramatically improve the computation speed of sophisticated mathematics.
- Eigen
- Armadillo
- CUSP - level interface for manipulating sparse matrices and solving sparse linear systems.
- CUV
-
Machine Learning Frameworks
- Shogun - source machine learning library that offers a wide range of efficient and unified machine learning methods.
- DLib
- Caffe
- Fido - weight, open-source, and highly modular C++ machine learning library. The library is targeted towards embedded electronics and robotics.
- Darknet
- Shogun - source machine learning library that offers a wide range of efficient and unified machine learning methods.
- OpenNN
- Dynet
- Fido - weight, open-source, and highly modular C++ machine learning library. The library is targeted towards embedded electronics and robotics.
- frugally-deep - only library for using Keras models in C++, supporting CNN. Currently only runs on CPU.
-
Reinforcement Learning
- RLLib (Saminda's) - a lightweight C++ template library that implements incremental, standard, and gradient temporal-difference learning algorithms in Reinforcement Learning. See the [paper](http://robocup.oss-cn-beijing.aliyuncs.com/symposium%2FRoboCup_Symposium_2015_submission_3.pdf) (PDF).
- RLlib - C++ library for reinforcement learning. See the paper "[A C++ Template-Based Reinforcement Learning Library: Fitting the Code to the Mathematics](http://www.jmlr.org/papers/v14/frezza-buet13a.html)", Hervé Frezza-Buet, Matthieu Geist.
-
Other Lists
- Awesome Machine Learning (C++ Section)
- http://mloss.org/software/ - machine learning OSS.
- Comparison of deep learning software - Wikipedia
-
Other Stuff
-
Machine Learning for Trading
- Optimal Asset Allocation using Adaptive Dynamic Programming
- Algorithm Trading using Q-Learning and Recurrent Reinforcement Learning
- The price impact of order book events. Journal of financial econometrics
- Q Learning for Trading
- Algorithm Trading using Q-Learning and Recurrent Reinforcement Learning
- The price impact of order book events. Journal of financial econometrics
- Optimal Asset Allocation using Adaptive Dynamic Programming
- Artificial Markets and Intelligent Agents
- Learning to Trade via Direct Reinforcement
- Reinforcement learning for trading systems and portfolios
- Agent Inspired Trading Using Recurrent Reinforcement Learning and LSTM Neural Networks
-
Categories
Sub Categories