Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Probabilistic Machine Learning: An Introduction

probml.github.io

Post reply on HN
Print view View original

21–30 of 59 posts

Re: Probabilistic Machine Learning: An Introduction

#21

Post by master_yoda_1 »

amkkma wrote: post #20
master_yoda_1 wrote: post #17

Earlier quoted context omitted.

Answer is not so black and white as everything in ml has to use probability. You can ignore this unless you are among 20 top researchers who are working on frontier of ml. Bayesian probabilistic techniques does not work or are very slow for any practical purpose.

But does it aid in understanding regular models, as they might have a bayesian interpretation?

Yeh for sure, but it's an overkill. It's like reading quantum mechanics to understand Newtonian mechanics. If you want to get a feel of bayesian ml here is an easier book, "Regression and Other Stories" https://avehtari.github.io/ROS-Examples/

Re: Probabilistic Machine Learning: An Introduction

#22

Post by SideQuark »

jbay808 wrote: post #15
joaorico wrote: post #7

The new edition has been split in two parts. The pdf draft (921 pages) and python code [1] of the first part are now available. The table of contents of the second part is here [2]. From the preface: "By Spring 2020, my draft of the second edition had swollen to about 1600 pages, and I was still not done. At this point, 3 major events happened. First, the COVID-19 pandemic struck, so I decided to “pivot” so I could s…

It's very encouraging to see Matlab losing ground in the educational space. I don't know why so many engineers let their foundational skills to be locked behind a proprietary ecosystem like that.

>I don't know why so many engineers let their foundational skills to be locked behind a proprietary ecosystem like that.

Because no open source toolkit can do what Matlab can do.

The same is true of a lot of high end software: Photoshop, pretty much any serious parametric CAD modeling system (say, SolidWorks), DaVinci Resolve, Ableton Live, etc. When a professional costs $100K+ to employ, paying a few grand to make them vastly more productive is a no brainer. If open source truly offered a replacement, then these costly programs would die. But there just isn't anything close for most work.

Matlab is used for massive amounts of precise numerical engineering design, modeling, and running systems. So while Python is good for some tasks, for the places Matlab shines Python is no where near usable. And before Python catches up in this space, I'd expect Julia to get there faster.

Re: Probabilistic Machine Learning: An Introduction

#23

Post by amkkma »

master_yoda_1 wrote: post #21
amkkma wrote: post #20

Earlier quoted context omitted.

But does it aid in understanding regular models, as they might have a bayesian interpretation?

Yeh for sure, but it's an overkill. It's like reading quantum mechanics to understand Newtonian mechanics. If you want to get a feel of bayesian ml here is an easier book, "Regression and Other Stories" https://avehtari.github.io/ROS-Examples/

Thanks. How's that relate to Gelman's BDA or statistical rethinking?

Re: Probabilistic Machine Learning: An Introduction

#24

Post by JHonaker »

master_yoda_1 wrote: post #10
JHonaker wrote: post #5

This is probably my favorite introductory machine learning book. The fact that he places almost everything in the language of graphical models is such a good common ground to build off. This really sets you up to realize that there is (and should be) a lot more to doing a good job in machine learning than simply minimizing an objective function. The answers you get depend on the model you create as do the questions y…

Agree with you. But none of this is useful for practical (applied) machine learning. I don't want to disappoint you but you can read it as machine learning porn, but otherwise don't waste time on it.

I mean, as a graduate student, it was definitely incredibly useful. As a practicing data scientist, I’d have to say that it’s also incredibly useful.

I’ve used this stuff, and more often, the ideas taught, to break down a problem into a tackle-able set of pieces more times than I can count.

Never underestimate the fundamentals. Too many of my colleagues use models without actually understanding any of it. I’ve debugged so many problems by looking at the technical details in original papers and textbooks.

Re: Probabilistic Machine Learning: An Introduction

#25

Post by rustyconover »

master_yoda_1 wrote: post #16
hnracer wrote: post #11

Earlier quoted context omitted.

Are you saying the book itself is ML porn?

Yes, unless you are among 20 top researchers who are working on frontier of ml. Bayesian probabilistic techniques does not work or are very slow for any practical purpose.

Turing.jl[1] is quite usable and isn't slow[2].

[1] - https://turing.ml/dev/ [2] - https://arxiv.org/abs/2002.02702

Re: Probabilistic Machine Learning: An Introduction

#26

Post by Nowado »

SideQuark wrote: post #22
jbay808 wrote: post #15

Earlier quoted context omitted.

It's very encouraging to see Matlab losing ground in the educational space. I don't know why so many engineers let their foundational skills to be locked behind a proprietary ecosystem like that.

>I don't know why so many engineers let their foundational skills to be locked behind a proprietary ecosystem like that. Because no open source toolkit can do what Matlab can do. The same is true of a lot of high end software: Photoshop, pretty much any serious parametric CAD modeling system (say, SolidWorks), DaVinci Resolve, Ableton Live, etc. When a professional costs $100K+ to employ, paying a few grand to make t…

Professional costs $100k+ to employ partially because only those able to afford those tools for training get into the field.

Re: Probabilistic Machine Learning: An Introduction

#27

Post by master_yoda_1 »

rustyconover wrote: post #25
master_yoda_1 wrote: post #16

Earlier quoted context omitted.

Yes, unless you are among 20 top researchers who are working on frontier of ml. Bayesian probabilistic techniques does not work or are very slow for any practical purpose.

Turing.jl[1] is quite usable and isn't slow[2]. [1] - https://turing.ml/dev/ [2] - https://arxiv.org/abs/2002.02702

Can it handle 1000 predictor with 1 million data points?

Re: Probabilistic Machine Learning: An Introduction

#28

Post by master_yoda_1 »

amkkma wrote: post #23
master_yoda_1 wrote: post #21

Earlier quoted context omitted.

Yeh for sure, but it's an overkill. It's like reading quantum mechanics to understand Newtonian mechanics. If you want to get a feel of bayesian ml here is an easier book, "Regression and Other Stories" https://avehtari.github.io/ROS-Examples/

Thanks. How's that relate to Gelman's BDA or statistical rethinking?

Bda is more advanced version of this book. Stats rethinking is also good and one can start from scratch as it has more code and less maths.

Re: Probabilistic Machine Learning: An Introduction

#29

Post by sjg007 »

jaredtn wrote: post #6

Quite excited to read this. Murphy does a great job of explaining concepts from first principles.

I think it would be extremely helpful to map the math into code. Nobody has done this as far as I've seen. I mean you can find Github repositories for some papers but really a set of explicit tutorials from the math to the code would be really helpful.

To say something is "machine learning", I think means that you should show the code not just equations and derivations.

I mean if you only show math and derivations, what's the point? To show off what you know? How is that helpful?

Re: Probabilistic Machine Learning: An Introduction

#30

Post by dklend122 »

master_yoda_1 wrote: post #28
amkkma wrote: post #23

Earlier quoted context omitted.

Thanks. How's that relate to Gelman's BDA or statistical rethinking?

Bda is more advanced version of this book. Stats rethinking is also good and one can start from scratch as it has more code and less maths.

Ty
Post reply on HN