Below are some resources I feel naturally complement or extend the scope of this lecture series. Please feel free to go through them, and suggest some more if you want!
Reference courses :
- Machine Learning - One of the most famous MOOCs around, available for free on Coursera.
- Machine learning Techniques - Course at IIT Kanpur, at the level of junior undergraduates / graduates
- Elements of Statistical Learning - free pdf copy available online.
UCI Repository Hosts a myriad array of different kinds of datasets. Also included are details of what the data is like, what benchmarks consider them, and what methods perform well. Good place to practice your data cleaning and modelling skills.
Computer Vision datasets Hosts a wide variety of video and image datasets.
USA Government Data Hosts a variety of USA specific data that has been collected by the government.
Aggregator Search engine for different kinds of data.
EU Data portal European Union collected datasets.
Kaggle hosts machine learning contests. There are some that are just for practice, and are a good way to build intuition about models, as well as understand how to clean up and actually apply models to real life data. Some contests also have prize money, so participation can be for more than just knowledge.
Example IPython Notebooks
Some more examples can be found in the course repository here. A lot more can be found from Scikit Learn’s documentation.
Neural network playground : lets you create toy neural networks to see the power, on different kinds of datasets. This is an amazing tool to understand how neural networks possibly work, and on the toy datasets, it is easy to see the combination of perceptrons learning together!
Jupyter Notebook : lets you create online jupyter notebooks. You can try out the majority of tutorials I have posted using this tool.
Stanford Tensorflow course This should be a good place to start for all of your neural network needs.
Tensorflow 1 : Part 1 of an introduction to Tensorflow, by Aadil.
Tensorflow 2 : Part 2 of an introduction to Tensorflow, by Aadil.
Other resources shall be put up later.