A collection of machine learning tools for classifying data. Includes Natural Language Processing.
|Tutorials to get you
|scikit-learn||Machine learning for Python||Useful cheat sheet|
|Yellow Brick||Yellowbrick is a suite of visual diagnostic tools that extend the Scikit-Learn API to allow human steering of the machine learning model selection process.|
|AstroML||AstroML is a Python module for machine learning and data mining built on numpy, scipy, scikit-learn, matplotlib, and astropy. It contains a growing library of statistical and machine learning routines for analyzing astronomical data in Python, loaders for several open astronomical datasets, and a large suite of examples of analyzing and visualizing astronomical datasets.|
|PyTorch||PyTorch is a deep learning framework for Python.||PyTorch Tutorials
Tutorials on GitHub
|pipeliner||Machine learning pipelines for R||Examples|
|TensorFlow||An open-source software library for Machine Intelligence.|
|Picasso||A free open-source visualizer for Convolutional Neural Networks.||Cloudy with a chance of tanks|
|IBM Watson||Watson can understand all forms of data, interact naturally with people, and learn and reason, at scale. You can analyze and interpret all of your data, including unstructured text, images, audio and video.|
Created by Arna Karick (@drarnakarick) following Astro Hack Week 2016. Based on Adrian–Price Whelan (@adrianprw), Dan Foreman–Mackey (@exoplaneteer), and Ben Nelson's Urban Goggles Astro Hack Week 2016 project (@AstroHackWeek)
Developed by the Astronomy Data & Computing Services (@AdacsAus) team for the 2017 Astronomical Society of Australia (ASA) Annual Meeting.
News & Resources
Siemens’ MindSphere is a cloud-based, open operating system for the Internet of Things (IoT). This white paper outlines how MindSphere makes data actionable and transforms it into measurable business success.
Companies new to the space can learn a great deal from early adopters who have invested billions into AI and are now beginning to reap a range of benefits. In this independent discussion paper, we examine investment in artificial intelligence (AI), describe how it is being deployed by companies that have started to use these technologies across sectors, and aim to explore its potential to become a major business disrupter.
To accelerate the pace of open machine-learning research, Google is developing the TensorFlow Research Cloud, a cluster of 1,000 Cloud TPUs that will be made available free of charge to support a broad range of computationally-intensive research projects.
The UK Royal Society recently published its major science policy report on Machine learning: the power and promise of computers that learn by example.
GitHub repository for the book "Introduction to Artificial Neural Networks and Deep Learning: A Practical Guide with Applications in Python."
A nice introduction to Support Vector Machine (SVM), a supervised machine learning algorithm which can be used for classification or regression problems. From the Yhat Blog.
A nice blog post by Gil Fewster about Google's recent AI "breakthrough".
Jake VanderPlas, Senior Data Scientist and Director of Research recently published the Python Data Science Handbook. This is a detailed guide to the most important Python tools for data science, covering IPython, Jupyter, NumPy, Pandas, Matplotlib, Scikit-Learn, and other tools.
GE Digital announced that it had entered into a definitive agreement to acquire machine learning technology company Wise.io. The acquisition will enable GE Digital to further accelerate development of advanced machine learning and data science offerings on the Predix platform. Berkeley-based Wise.io was founded in 2013 by UC Berkeley astronomer Prof. Joshua Bloom, to bring high-performance machine learning to the business world.
An intensive seven-week professional training fellowship for scientists and engineers with machine learning experience to learn cutting-edge techniques in deep learning and join top AI teams in Silicon Valley and New York City.