Skip to content

Latest commit

 

History

History
executable file
·
249 lines (182 loc) · 20.9 KB

AI.md

File metadata and controls

executable file
·
249 lines (182 loc) · 20.9 KB

AI :: Artificial Intelligence, Cognitive Science, Machine Learning {(Un)Supervised/RL}, Neural Nets, NLP, etc...



§1. AI

  • simpleai :: Simple artificial intelligence utilities.

§2. DATA SCIENCE

  • engarde :: A library for defensive data analysis.
  • gqn-datasets :: Datasets used to train Generative Query Networks (GQNs) in the ‘Neural Scene Representation and Rendering’ paper.
  • python-seminar :: Python Computing for Data Science.
Resources

§3. MACHINE LEARNING.

  • ConfidenceWeighted :: Confidence weighted classifier.
  • Faceless :: A port of ICAAM library by Luca Vezzaro to Python for Face Tracking based on Active Appearance Models.
  • featureforge :: A set of tools for creating and testing machine learning features, with a scikit-learn compatible API.
  • Foxhound :: Scikit-learn inspired library for gpu-accelerated machine learning.
  • fuel :: A data pipeline framework for machine learning.
  • hips-lib :: Library of common tools for machine learning research.
  • MachineLearning :: Materials for the Wednesday Afternoon Machine Learning workshop.
  • Machine Learning Video Library.
  • Masque :: Experiments on Deep Learning and Emotion Classification.
  • MILK :: Machine Learning Toolkit.
  • MLOSS.org
  • MLTRP :: Machine Learning and the Traveling Repairman Problem.
  • Morris_counter is a Probabilistic Morris Counter (counts 2^n using e.g. just a byte).
  • MLTP :: ML Timeseries Platform.
  • ProFET :: Protein Feature Engineering Toolkit for Machine Learning.
  • pyHANSO :: Python Implementation of Michael Overton's HANSO (Hybrid Algorithm for Non-Smooth Optimization).
  • pyklsh :: Python implementation of Kernelized Locality Sensitive Hashing
  • PyML is an interactive object oriented framework for machine learning written in Python, with support for classification and regression, including Support Vector Machines (SVM), feature selection, model selection, syntax for combining classifiers and methods for assessing classifier performance.
  • Rambutan :: A python wrapper for caffe which aims at providing a simple, pythonic, interface for users so that users can define, train, and evaluate deep models in only a few lines of code. It requires that caffe and pycaffe are both built properly.
  • RAMP :: Rapid Machine Learning Prototyping in Python.
  • python-recsys :: A python library for implementing a recommender system.
  • Sixpack :: a language-agnostic a/b-testing framework. Documentation
  • TPOT :: A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming. A blog post explaining the same: http://www.randalolson.com/2016/05/08/tpot-a-python-tool-for-automating-data-science/
  • PyCM :: PyCM is a multi-class confusion matrix library written in Python that supports both input data vectors and direct matrix, and a proper tool for post-classification model evaluation that supports most classes and overall statistics parameters. PyCM is the swiss-army knife of confusion matrices, targeted mainly at data scientists that need a broad array of metrics for predictive models and an accurate evaluation of large variety of classifiers.
Resources

§3.1. Deep Learning. span id="3-1-Deep-Learning">

Resources
  • DeepLearningTutorials :: Deep Learning Tutorial notes and code. See the wiki for more info.
  • Deep Learning Part 1: Comparison of Symbolic Deep Learning Frameworks.
  • handson-ml :: A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in python using Scikit-Learn and TensorFlow.
  • handson-ml2 :: Version-2 of the series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.

§3.2. Classification Algorithms. span id="3-2-Classification-Algorithms">

Resources

Naive Bayes

§3.3. Graph Theory. span id="3-3-Graph-Theory">

Resources

§3.4. GPU. span id="3-4-GPU">

  • cuML :: is a suite of libraries that implement machine learning algorithms and mathematical primitives functions that share compatible APIs with other RAPIDS projects.

§4. NLP. span id="4-NLP">

  • Broca :: Various useful NLP algos and utilities for rapid NLP prototyping.
  • commonast :: A common AST description for Python.
  • Fairseq :: A sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling and other text generation tasks.
  • Gensim is a Python library for topic modelling, document indexing and similarity retrieval with large corpora for natural language processing (NLP) and information retrieval (IR). Source Code.
  • Geiger :: An automated system for grouping similar comments and then identifying the best representative from each group.
  • Glove-python :: Toy Python implementation of http://www-nlp.stanford.edu/projects/glove/
  • Gramformer :: A framework for detecting, highlighting and correcting grammatical errors on natural language text.
  • IEPY :: An open source tool for Information Extraction focused on Relation Extraction.
  • JPKyteaTokenizer :: A Japanese tokenizer with KyTea for nltk.
  • Mykytea-python :: Python wrapper for KyTea.
  • NLTK :: Natural Language ToolKit to manipulate human language data. Source Code
  • nupic.fluent :: A platform for building language / NLP-based applications using NuPIC and CEPT.
  • Quepy :: A python framework to transform natural language questions to queries in a database query language.
  • Parrot_Paraphraser :: Parrot is a paraphrase based utterance augmentation framework purpose built to accelerate training NLU models.
  • PLY :: Python Lex-Yacc. http://www.dabeaz.com/ply/index.html
  • SAMR :: An entry to kaggle's 'Sentiment Analysis on Movie Reviews' competition.
  • Suggester :: The heart for full-text auto-complete web services.
  • TextGridTools :: Read, write, and manipulate Praat TextGrid files with Python.
  • txtai:: builds an AI-powered index over sections of text & supports building text indices to perform similarity searches and create extractive question-answering based systems.
  • word_cloud :: A little word cloud generator in Python.

§4.1. Computational Linguistics span id="4-1-Computational-Linguistics">

  • spaCy :: a library for advanced Natural Language Processing in Python and Cython; with pretrained pipelines and currently supports tokenization and training for 60+ languages that features neural network models for tagging, parsing, named entity recognition, text classification and more.

§4.1.1. Named Entity Recognition. span id="4-1-1-Named-Entity-Recognition">

  • CLNER :: The code is for the ACL-IJCNLP 2021 paper "Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning".
  • mt-dnn :: This PyTorch package implements the Multi-Task Deep Neural Networks (MT-DNN) for Natural Language Understanding.

§4.2. Digital Humanities. span id="4-2-Digital-Humanities">

§4.3. Screen Reading

  • wordgraph :: This project supports creating English-language text from a graph description for those doing screen reading for vision-impaired people, or just people who like to listen to graphs while jogging, or just to get a handle on what's going on.
  • Resources
    • STT with HMM :: Single Speaker Speech Recognition with Hidden Markov Models.

§4.4. Speech Recognition

Resources

§4.5. Transformers. span id="4-5-Transformers">

  • BERT :: TensorFlow code and pre-trained models for 24 smaller BERT models (English only, uncased, trained with WordPiece masking) referenced in Well-Read Students Learn Better: On the Importance of Pre-training Compact Models.
  • Transformers :: State-of-the-art Natural Language Processing for Jax, PyTorch and TensorFlow.

  • bsuite :: A collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent.
  • Tensortrade :: An open source reinforcement learning framework for training, evaluating, and deploying robust trading agents.

  • AIQC :: is an open source framework for rapid & reproducible deep learning.

  • tensor2tensor :: Tensor2Tensor (T2T) Transformers is a modular and extensible library and binaries for supervised learning with TensorFlow and with support for sequence tasks. It is actively used and maintained by researchers and engineers within the Google Brain team.
Resources

Neural Networks

  • BinaryConnect :: Training Deep Neural Networks with binary weights during propagations.
  • BinaryNet :: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1.
  • NAMAS :: Neural Attention Model for Abstractive Summarization.
  • SparkNet :: Distributed Neural Networks for Spark.
  • pylearn2 : A Machine Learning library based on Theano.
  • Tensorflow :: Open source software library for numerical computation using data flow graphs. Source code on GH.
    • models :: Models built with TensorFlow.
    • Resources: TensorFlow-Tutorials :: Simple tutorials using Google's TensorFlow Framework.
  • theano-nlp :: Tools and datasets for NLP in Theano.

Pre-Trained Models

  • Spiral :: A pre-trained model for unconditional 19-step generation of CelebA-HQ images.
Resources