AI / ML Notes

back

Tasks

A task can be considered complete when I have reviewed the material AND added notes here.

• Copy notes from the other notes repository
• NLP / NLU tasks
• Review material from the Machine Learning nanodegree
• Review material from the AI nanodegree
• Review material from the SDCND nanodegree
• Complete the SDCND nanodegree
• Rewatch Deep Reinforcement Learning nanodegree content
• Take linear algebra notes
• Take calculus notes
• Take probability theory notes
• Understand core AI and ML algorithms at a fundamental level (be able to talk about them clearly and concisely without looking up the details)

Optimisation Algorithms

• Convex Optimisation
• Hill Climbing

NLP / NLU

• Things to Learn About
• NLPND: Intro to NLP
• NLPND: Text Processing
• NLPND: Spam Classification With Naive Bayes
• NLPND: Part of Speech Tagging with HMMs
• Embeddings
• Tokenisation

Jay Alammar’s Illustrated Blog Posts: https://jalammar.github.io/

• Visualizing A Neural Machine Translation Model (Mechanics of Seq2seq Models With Attention)
• The Illustrated Transformer
• The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning)
• The Illustrated GPT-2 (Visualizing Transformer Language Models)

• The Illustrated Word2vec

• Deconstructing BERT: Distilling 6 Patterns from 100 Million Parameters

Reinforcement Learning

Supervised Learning

Unsupervised Learning

Deep Learning

AI in Production

Vocabulary

Maths