Review : Stanford's Online Artificial Intelligence Courses - Deep Learning and Machine Learning

Hello!


I have been enrolled at Stanford and have been taking their courses online. Here are my few cents on the ones I have taken so far.

CS224n - Natural Language Processing with Deep Learning (Prof. Manning)

• Difficulty: 4/5 (Moderate)
• What to expect: 
• Get exposed to State-of-the-Art (SoTA) Deep Learning techniques applied to NLP. Key topics: 
• Question and Answering
• Text Summarization
• Parts of Speech tagging
• Sequence-to-Sequence models
• Transformers
• Gives you a very good overview of where NLP is headed, homeworks are challenging but allow you to implement latest neural architectures to solve various language problems.
• My class project: BertQA (99* stars on github) - Won Best Project Award in the class

CS231n - Convolutional Neural Networks for Visual Recognition (Prof. Li and Justin Johnson)

• Difficulty: 4/5 (Moderate)
• What to expect: 
• Extensive overview of latest trends in Computer Vision techniques across different domains and applications - 
• Discriminative models
• Unsupervised techniques
• Neural Architecture layers and intutions 
• Segmentation
• Generative Techniques
• Style Transfer
• Homeworks are the best part of the class which allow you to implement a variety of Neural Layers and get in-depth intuition of how deep learning actually works.
• I would suggest some familiarity with matrix calculus and probability for this course.
• My class project: Spatio-Temporal Adversarial Video Super Resolution

CS221 - Artificial Intelligence - Principles and Techniques (Prof. Liang and Prof. Sadigh)

• Difficulty: 4.5/5 (Heavy)
• What to expect: 
• This is one of the most "dense" classes I have come across at Stanford. The nature of the class is such that it is trying to fit in this huge umbrella of AI topics within a quarter - which is what makes it challenging. Topics include - 
• Search
• Markov Decision Process
• Reinforcement Learning (RL)
• Adversarial Games
• Constraint Satisfaction problems
• Bayesian Networks (BN)
• Amongst these, Reinforcement Learning and Bayesian Networks are conceptually heavy topics which require some extra effort.
• That being said, the topics are interesting and makes you appreciate the latest trends in AI and draw parallels from traditional techniques. 
• Homeworks are weekly and can take time but are fun for the most part! You build your own Pacman game. 
• My class project: 
• Work in progress (to be updated shortly)

Feel free to send in any other questions you would like for me to answer.

Thank you,

Ankit Chadha