This is a very incomplete and subjective selection of resources to learn about the algorithms

  • Computer vision
  • Natural Language Processing
  • Neural Networks
  • Reinforcement Learning

  1. OpenFace – Free and open source face recognition with deep neural networks.
  2. Face_recognition – Face recognition library that recognizes and manipulates faces from Python or from the command line
  1. Openpose – A real-time multi-person keypoint detection library for body, face, hands, and foot estimation
  2. IoT Owl – Light face detection and recognition system with huge possibilities, based on Microsoft Face API and TensorFlow made for small IoT devices like raspberry pi
  1. Scikit-Image – A collection of algorithms for image processing in Python.
  2.  PyTorchCV – A PyTorch-Based Framework for Deep Learning in Computer Vision

  1. Rasa – A « machine learning framework to automate text-and voice-based conversations. »
  2. DeepPavlov is an open-source conversational AI library built on TensorFlow, Keras and PyTorch.
  1. YAlign – A sentence aligner, a friendly tool for extracting parallel sentences from comparable corporation
  2. Sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search
Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow

  1. NeuralTalk - NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences
  2. nn_builder - nn_builder is a python package that lets you build neural networks in  line
  1. Gym - OpenAI Gym is a toolkit for developing and comparing reinforcement learning algorithms.
  2. Prophet is a procedure for forecasting time series data based on an additive model where non-linear trends are fit with yearly, weekly, and daily seasonality, plus holiday effects