— In the News —
Andrew Ng is one of the leading experts in machine learning. He's the Chief Scientist of Baidu, co-founder of Coursera, and an Associate Professor at Stanford. This interview offers his insights about challenges facing AI and "evil killer robots."
TeraDeep is a startup that wants you to revive your old devices by giving them the power of Deep Learning. Here's how.
— Tools and Techniques —
Brilliant weekend project by Randy Olson! Using a variety of machine learning tricks, here's how he determined the optimal search strategy for finding Waldo.
Ever wonder how music recognition engines work? This is a great read with lots of diagrams, code snippets, and links to explore.
This article follows the story of a concept devised in 1943 to a Kaggle competition in 2015. It shows that a single artificial neuron can get 0.95 AUC on an NLP sentiment analysis task. This is a nice exploration of how it works.
— Resources —
pandas is a Python library for doing data analysis. It's really fast and lets you do exploratory work incredibly quickly. Here's a great cookbook by Julia Evans that's full of instructive recipes for performing common tasks. Highly recommended.
Awesome curated collection of IPython and Jupyter Notebooks. There's a lot to explore here... neural nets, pandas, python for data mining, D3 for MatPlotlib, etc, etc, etc. Highly recommended.
The title says "Abridged" but there's a lot of good stuff here. This is a well-linked collection of software, research, and talks for a variety of machine learning topics, such as Deep Learning, Computer Vision, Natural Language Processing, Visualization, GPU Learning, and Optimization.
— Data Viz —
Here's an easy-to-use, web-friendly color conversion and interpolation library for Python. This is well-documented and greatly simplifies data presentation.
This is a great overview of strategies for visualizing data that's associated with a map. They're not all obvious! This is well-presented with lots of diagrams.