Hello :) Today is Day 93!
A quick summary of today:
- covered lecture 1.2 Node embeddings on XCS224W: ML with Graphs
- from Probabilistic Machine Learning: An Introduction, covered:
- chapter 5: Decision theory
- chapter 6: information theory
- chapter 7: linear algebra
First, my notes from lecture 1.2 Node embeddings for graphs
Covered topics: node embeddings: encoder and decoder, random walk, unsupervised feature learning, random walk optimization, negative sampling, node2vec, anonymous walks, learning walk embeddings
Next, from Probabilistic ML: An introduction by Kevin Murphy
Chapter 5: Decision theory
Covered topics: classification problems, ROC curve, Precision-Recall curves, F-scores, Regression problems
Chapter 6: Information theory
Covered topics: entropy, entropy of discrete random variables, cross entropy, conditional entropy, perplexity
Chapter 7: Linear algebra
Covered topics: notations(vectors, matrices, tensors, vector spaces, linear map, properties), matrix multiplication, inversion, EVD, SVD
Tomorrow, I believe I will continue with the 1.3 lecture from XCS224W: PageRank, Personalised PageRank and Matrix Factorization.
That is all for today!
See you tomorrow :)