Find file Copy path
Fetching contributors…
Cannot retrieve contributors at this time
150 lines (146 sloc) 14.3 KB

Python Software, Libraries, and Packages

  • Artificial Intelligence (AI), deep learning, neural networks
    • Torch - A scientific computing framework with wide support for machine learning algorithms that puts GPUs first
    • Caffe - A deep learning framework made with expression, speed, and modularity in mind
    • DL4J - Open-Source, Distributed, Deep Learning Library for the JVM
    • Theano - Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently [DEPRECATED after v1.0]
    • TensorFlow - Open source software library for numerical computation using data flow graphs
    • Amazon Deep Scalable Sparse Tensor Network Engine (DSSTNE) - An Amazon developed library for building Deep Learning (DL) machine learning (ML) models
    • Keras: Deep Learning library for Theano and TensorFlow - A high-level neural networks library, written in Python and capable of running on top of either TensorFlow or Theano
    • Blocks - A framework that helps you build and manage neural network models on using Theano
    • Lasagne - A lightweight library to build and train neural networks in Theano
    • MXNet - Flexible and Efficient Library for Deep Learning
    • Gluon - Amazon's MXNet-based deep learning framework
    • Sonnet - TensorFlow-based neural network library
    • Spotlight - Deep recommender models using PyTorch
    • PyBrain - Python-Based Reinforcement Learning, Artificial Intelligence and Neural Network Library
    • Chainer - A Powerful, Flexible, and Intuitive Framework for Neural Networks
    • NuPIC - An open source project based on a theory of neocortex called Hierarchical Temporal Memory (HTM)
    • Neon - Python-based deep learning library
    • OpenCV - An open source computer vision and machine learning software library
    • Neurolab - A simple and powerful Neural Network Library for Python
    • SimpleAI - Implements many of the artificial intelligence algorithms described on the book "Artificial Intelligence, a Modern Approach", from Stuart Russel and Peter Norvig
    • Nolearn - Utility modules that are helpful with machine learning tasks
    • Hebel - GPU-Accelerated Deep Learning Library in Python
    • DeepPy - Deep learning in Python
    • PyTorch - Facebook's optimized tensor library for deep learning using GPUs and CPUs
    • Pyro - Uber's deep probabilistic programming language
  • Natural Language (NLP, NLG, NLU)
    • Natural Language Toolkit - A leading platform for building Python programs to work with human language data
    • spaCy - Industrial-Strength Natural Language Processing in Python
    • TextBlob - A Python (2 and 3) library for processing textual data
    • Gensim - Topic modelling for humans
    • fastText - Pre-trained word vectors for 90 languages, trained on Wikipedia using fastText
    • DeepSpeech - Mozilla's TensorFlow implementation of Baidu's DeepSpeech architecture
  • Machine Learning
    • Scikit-image - A collection of algorithms for image processing
    • Scikit-learn - A Python module for machine learning
    • Scikit-feature - Open-source feature selection repository in python
    • Shogun - Machine learning toolbox that provides a wide range of unified and efficient Machine Learning (ML) methods
    • mlpy - A Python module for Machine Learning built on top of NumPy/SciPy and the GNU Scientific Libraries
    • Annoy - Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
    • PyMVPA - PyMVPA stands for MultiVariate Pattern Analysis (MVPA) in Python
    • Deap - A novel evolutionary computation framework for rapid prototyping and testing of ideas
    • Vowpal Wabbit (Fast Learning) - Out-of-core learning system
    • CoreML - Apple's machine learning framework

R Software, Libraries, and Packages

  • Artificial Intelligence (AI)
    • nnet - Software for feed-forward neural networks with a single hidden layer, and for multinomial log-linear models
    • neuralnet - Training of neural networks using backpropagation, resilient backpropagation with (Riedmiller, 1994) or without weight backtracking (Riedmiller and Braun, 1993) or the modified globally convergent version by Anastasiadis et al. (2005)
    • c50 - C5.0 decision trees and rule-based models for pattern recognition
  • Natural Language (NLP, NLG, NLU)
  • Natural language (NLP, NLG, NLU)
  • Machine Learning
    • caret - Misc functions for training and plotting classification and regression models
    • randomForest - Classification and regression based on a forest of trees using random inputs
    • e1071 - Functions for latent class analysis, short time Fourier transform, fuzzy clustering, support vector machines, shortest path computation, bagged clustering, naive Bayes classifier, ...
    • ISLR - The collection of datasets used in the book "An Introduction to Statistical Learning with Applications in R"
    • lme4 - Fit linear and generalized linear mixed-effects models
    • nlme - Fit and compare Gaussian linear and nonlinear mixed-effects models
    • mda - Mixture and flexible discriminant analysis, multivariate adaptive regression splines (MARS), BRUTO, ...
    • lasso2 - Routines and documentation for solving regression problems while imposing an L1 constraint on the estimates
    • lars - Efficient procedures for fitting an entire lasso sequence with the cost of a single least squares fit
    • glmnet - Extremely efficient procedures for fitting the entire lasso or elastic-net regularization path for linear regression, logistic and multinomial regression models, Poisson regression and the Cox model
    • rpart - Recursive partitioning for classification, regression and survival trees
    • kernlab - Kernel-based machine learning methods for classification, regression, clustering, novelty detection, quantile regression and dimensionality reduction
    • gbm - Includes regression methods for least squares, absolute loss, t-distribution loss, quantile regression, logistic, multinomial logistic, Poisson, Cox proportional hazards partial likelihood, AdaBoost exponential loss, Huberized hinge loss, and Learning to Rank measures (LambdaMart)
    • class - Various functions for classification, including k-nearest neighbour, Learning Vector Quantization and Self-Organizing Maps
    • gmodels - Various R programming tools for model fitting
    • princurve - Fits a principal curve to a data matrix in arbitrary dimensions

Non-language Specific

APIs, SaaS, and Platforms