Fast Recurrent Networks Library

PRNN A fast implementation of recurrent neural network layers in CUDA. Introduction For a GPU, the largest source of on-chip memory is distributed among the individual register files of thousands of threads. For exa

Related Repos

bwilbertz RLightGBM, R interface to Light Gradient Boosting Machine library LightGBM is a gradient boosting framework that uses tree based learning algorithms. It is designed to be distributed and efficient with the following advantages:

hszhao Pyramid Scene Parsing Network

IntelLabs pWord2Vec This is a C++ implementation of word2vec that is optimized on Intel CPUs, particularly, Intel Xeon and Xeon Phi (Knights Landing) processors. It supports the "HogBatch" parallel SGD as described in a NIPS workshop paper

mariusmuja FLANN - Fast Library for Approximate Nearest Neighbors FLANN is a library for performing fast approximate nearest neighbor searches in high dimensional spaces. It contains a collection of algorithms we found to work best for near

100 Cranium is a portable, header-only, feedforward artificial neural network library written in vanilla C99. It supports fully-connected networks of arbitrary depth and structure, and should be reasonably fast

olmallet81 GALGO-2.0 Genetic Algorithm in C++ with template metaprogramming and abstraction for constrained optimization. Description GALGO is a C++ template library, header only, designed to solve a problem under constraints (o

yixuan tinydnn Introduction tinydnn is an (experimental) R wrapper of the tiny-dnn library for implementing Deep Neural Networks (DNN). The largest advantage of tiny-dnn over other deep learning frameworks is its minimal depe

mldbai MLDB is the Machine Learning Database by MLDB is an open-source database designed for machine learning. You can install it wherever you want and send it commands over a RESTful API to store data, explore it u