smythfoam

Machine Learning

Based on the list first drawn up for my talk “Straight outta Swampland” at the ITF KU Leuven in January 2020. If you get the joke and are interested, then feel free to poke me for the slides.

Specific topics are covered in their own pages [NLP], [ComputerVision], [TimeSeries] and [AGI]

The classical canon

Introduction to Statistical Learning, Witten et al http://faculty.marshall.usc.edu/gareth-james/ISL/

The Elements of Statistical Learning, Hastie et al https://web.stanford.edu/~hastie/ElemStatLearn/

Artificial Intelligence: A Modern Approach, Stuart Russell and Peter Norvig, http://aima.cs.berkeley.edu/

Pattern Recognition and Machine Learning, Bishop https://cds.cern.ch › record › files › 9780387310732_TOCPattern Recognition and Machine Learning

Deep Learning, Goodfellow et al https://www.deeplearningbook.org

Dive into Deep Learning https://arxiv.org/abs/2106.11342

Probabilistic Machine Learning: An Introduction by Kevin Patrick Murphy. https://probml.github.io/pml-book/book1.html

Neural Networks and Deep Learning by Michael Nielsen. nhttp://neuralnetworksanddeeplearning.com/

https://camdavidsonpilon.github.io/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers/

https://research.facebook.com/blog/2021/12/introducing-bean-machine-a-probabilistic-programming-platform-built-on-pytorch/

MOOCs and other tutorials

Pen and Paper Exercises in Machine Learning https://arxiv.org/abs/2206.13446

https://marcotcr.github.io/lime/tutorials/Lime%20-%20basic%20usage%2C%20two%20class%20case.html good original LIME example

https://classic.d2l.ai/index.html - Smola et al, Dive into Deep Learning

https://www.coursera.org/learn/machine-learning - classical ml.

https://www.deeplearning.ai/ - deep.

https://www.fast.ai/ - even deeper man.

https://arxiv.org/abs/1803.08823 - spot my bias.

https://developers.google.com/machine-learning/guides/rules-of-ml

Interpretability: https://twitter.com/hima_lakkaraju/status/1390754121322467330?s=11

Podcasts

TWIMLAI

Datacamp

Other resources

In no particular order

colab.research.google.com

Background: https://mml-book.com/

Awesome lists: https://github.com/sindresorhus/awesome

https://minimum-viable-data-scientist.readthedocs.io/

https://www.textbook.ds100.org/intro

https://developers.google.com/machine-learning/crash-course/

https://project-awesome.org/hangtwenty/ dive-into-machine-learning

https://paperswithcode.com/ - It’s paper with code.

https://callingbullshit.org

** https://fleuret.org/ee559/ **

https://colah.github.io

http://www.arxiv-sanity.com - The ML ArXiV is otherwise impossible to follow.

https://www.jeremyjordan.me/evaluating-a-machine-learning-model/

https://explained.ai/

DEEP LEARNING INTERVIEWS https://arxiv.org/abs/2201.00650

Distill.pub

Meetups

You can attend or help out at Meetups and Hackathons: We learn machine learning, Data Science meetups, Tensorflow meetup, NLP meetups.

Papers