AI Resources¶
These resources were curated by students who took the class.
Acknowledgements
- Felipe Martins
- Brandon Odegard
- Jorge E Gil
- Cheryl Roberts
Udacity¶
- Udacity AI Nanodegree - [$800 / term (2 terms)] - https://www.udacity.com/course/artificial-intelligence-nanodegree–nd889
- Udacity Intro to AI - https://www.udacity.com/course/intro-to-artificial-intelligence–cs271
- Udacity - GT Knowledge-Based AI - [Free] - https://www.udacity.com/course/knowledge-based-ai-cognitive-systems–ud409
- Udacity - GT - AI for Robotics - [Free] - https://www.udacity.com/course/artificial-intelligence-for-robotics–cs373
- Udacity - GT - Reinforcement Learning - [Free] - https://www.udacity.com/course/reinforcement-learning–ud600
- Udacity - GT - Machine Learning - [Free] - https://www.udacity.com/course/machine-learning–ud262
GitHub Resources¶
- Curated Awesome AI - https://github.com/owainlewis/awesome-artificial-intelligence
- Curated Awesome Python - https://github.com/vinta/awesome-python
- Curated Awesome ML - https://github.com/josephmisiti/awesome-machine-learning
Coursera¶
- Machine Learning by Andrew Ng - https://www.coursera.org/learn/machine-learning
MIT OCW¶
- MIT Artificial Intelligence - https://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-034-artificial-intelligence-fall-2010/
Berkeley¶
The AI videos/slides at Berkeley are very good, especially on the topic of Reinforcement learning. Look for the lectures on MDPs and RL and test your knowledge with the “pacman” agents and the robot crawler (my favorite):
http://ai.berkeley.edu/home.html
Also, here are some useful materials for Deep Learning at Stanford. I highly recommend the first sections in Module 1 where they compare k-NN to Neural Networks and all of Module 3 on Convolutional Networks. The NLP content I have less specific pointers in at the moment.
- Convolutional Neural Networks: http://cs231n.github.io/
- Natural Language Processing: http://cs224d.stanford.edu/syllabus.html