News for hackers. Stuff that matters.

A comment on Ask HN: Engineers from non-CS background, how did you pivot into ML/AI?. Parent comment

Re:Ask HN: Engineers from non-CS background, how did you piv... by boltzmannbrain on Monday December 31, 2018 @06:09PM (#18797668)
> study textbooks. Do exercises. Treat it like academic studying

This. Highly recommend Russel & Norvig [1] for high-level intuition and motivation. Then Bishop's "Pattern Recognition and Machine Learning" [2] and Koller's PGM book [3] for the fundamentals.

Avoid MOOCs, but there are useful lecture videos, e.g. Hugo Larochelle on belief propagation [4].

FWIW this is coming from a mechanical engineer by training, but self-taught programmer and AI researcher. I've been working in industry as an AI research engineer for ~6 years.

[1] https://www.amazon.com/Artificial-Intelligence-Modern-Approa...

[2] https://www.amazon.com/Pattern-Recognition-Learning-Informat...

[3] https://www.amazon.com/Probabilistic-Graphical-Models-Princi...

[4] https://youtu.be/-z5lKPHcumo

[ Parent | on HN ]
Re:Ask HN: Engineers from non-CS background, how did you piv... by magoghm on Monday December 31, 2018 @08:36PM (#18798347)
I would also include some books about statistics. Two excellent introductory books are:

Statistical Rethinking https://www.amazon.com/Statistical-Rethinking-Bayesian-Examp...

An Introduction to Statistical Learning http://www-bcf.usc.edu/~gareth/ISL/

[ Parent | on HN ]
Re:Ask HN: Engineers from non-CS background, how did you piv... by jimmy-dean on Monday December 31, 2018 @08:04PM (#18798231)
Oof those are all dense reads for a new comer... For a first dip into the waters I usually suggest Introduction to Statistical Learning. Then from there move into PRML or ESL. Were you first introduced to core ML through Bishop? +1 for a solid reading list.
[ Parent | on HN ]
Re:Ask HN: Engineers from non-CS background, how did you piv... by sampo on Monday December 31, 2018 @08:15PM (#18798273)
PGMs were in fashion in 2012, but by 2014 when Deep Learning had become all the rage, I think PGMs almost disappeared from the picture. Do people even remember PGMs exist now in 2019?
[ Parent | on HN ]
Re:Ask HN: Engineers from non-CS background, how did you piv... by KidComputer on Monday December 31, 2018 @08:32PM (#18798335)
You'll find plate models, PGM junk, etc in modern papers on explicit density generative models and factorizing latents on such models.
[ Parent | on HN ]
Re:Ask HN: Engineers from non-CS background, how did you piv... by srean on Tuesday January 01, 2019 @01:37AM (#18799265)
Fashion is relevant only if you want to approach it as a fashion industry.
[ Parent | on HN ]
Re:Ask HN: Engineers from non-CS background, how did you piv... by vazamb on Monday December 31, 2018 @09:22PM (#18798522)
PGMs also provide the intuition behind GANs and variational autoencoders.
[ Parent | on HN ]
Re:Ask HN: Engineers from non-CS background, how did you piv... by godelmachine on Monday December 31, 2018 @08:54PM (#18798413)
Hands up for Bishop and Russel Norvig.

Russel Norvig should be treated as a subtle intro to AI.

The start Bishop to understand concepts.

[ Parent | on HN ]