It isn’t easy to begin studying Machine Learning. There are just so many resources available today and a lot of enthusiasts never really get started. Things are evolving and changing so fast that it can make a persons head spin. It can be hard to find a place to start. Today we are going to go over a few notable projects worth learning about. Hopefully this list can help you begin.
TensorFlow
TensorFlow is an open source library that makes great usage of graphs and computation. The flexible nature of this system means that you can do a whole lot without a single line of code. You can launch computation on multiple GPU’s and CPU’s. Furthermore, it comes with a a visual toolkit called tensor board.
Scikit-learn
Scikit-learn is a module for Python. The project began as a Google Summer of Code project but has grown since due to many different people who have volunteered to improve it.
Chainer
Chainer is a framework for deep learning. It is Python based and aims to be very flexible. It supports CUDA/cuDNN and uses CuPY
Theano
Theano is a Python library written to allow users to define, optimize and evaluate mathematics arrays that are multidimensional.
Keras
Keras is written in Python and is a high level neural network API that can run on TensorFlow or Theano. Its focus is on enabling rapid experimentation.
PyTorch
A Python package that provides GPU acceleration, and Tensor computation
Shogun
A machine learning toolbox which can provide users with a wide range of efficient learning methods. It allows for the combination of multiple data representations, classes and has general purpose tools packaged into it.
Gensim
A Python library for indexing topic modeling and similarity retrieval. Made for natural language processing and information retrieval. It has an intuitive interface, multi-core implementation of algorithms and can work with computer clusters.
