41–50 of 53 posts
Is this aimed at undergrads or practicing engineers? What's the math background needed?
Tangentially related: It appears that TD ideas pop up in diffusion models, VAEs and neural net training dynamics. Any author/reading advice on links between thermodynamics, information, and neural nets?
There's a free 2022 textbook: https://direct.mit.edu/books/oa-monograph/5299/Active-Infere...
And a brand new one (though it's a bit pricey): https://mitpress.mit.edu/9780262050951/fundamentals-of-activ...
great job, thank you for this teacher!
This is awesome. Also, this quote feels relevant: "Ludwig Boltzmann, who spent much of his life studying statistical mechanics, died in 1906, by his own hand. Paul Ehrenfest, carrying on the work, died similarly in 1933. Now it is our turn to study statistical mechanics." - David Goodstein's States of Matter, Introduction
ha yes :-) Carnot died of cholera aged 36, and Rudolf Diesel committed suicide too. Maybe I should add an appendix about mental health at the end!
This is awesome. Also, this quote feels relevant: "Ludwig Boltzmann, who spent much of his life studying statistical mechanics, died in 1906, by his own hand. Paul Ehrenfest, carrying on the work, died similarly in 1933. Now it is our turn to study statistical mechanics." - David Goodstein's States of Matter, Introduction
Tangentially related: It appears that TD ideas pop up in diffusion models, VAEs and neural net training dynamics. Any author/reading advice on links between thermodynamics, information, and neural nets?
Since you mention VAEs: you might be interested in Active Inference, which is built on minimizing variational free energy. Same E−TS form as the thermodynamic kind (Helmholtz free energy), so it does fit your thermo/info/NN question. And the negative free energy is equivalent to the evidence lower bound used in generative models like VAEs. Lots of really fascinating connections between all of these topics :) There's…
This is awesome. Also, this quote feels relevant: "Ludwig Boltzmann, who spent much of his life studying statistical mechanics, died in 1906, by his own hand. Paul Ehrenfest, carrying on the work, died similarly in 1933. Now it is our turn to study statistical mechanics." - David Goodstein's States of Matter, Introduction
I found this article[1] by the author[2] that explain their motivation for the book. It has lots of deep insights about the textbook publishing industry and definitely worth a read.
[1] https://framablog.org/2022/01/20/mais-ou-sont-les-livres-uni... and auto-translation to EN for ppl who don't speak French: https://framablog-org.translate.goog/2022/01/20/mais-ou-sont...
Nice. Good to see actual hard science books popularized and available for free. The textbook industry is a criminal cartel shafting both the students/knowledge seekers and authors/professors. Hence i really appreciate the way you have made the pdf available both for free and for a nominal price; so thank you. We need more hard science (Physics/Chemistry/Biology/etc.) content (books/articles/videos/etc.) on HN. For ex…
I used to think that way about the publishing industry too, but I now think that this description is not deserved. Just observing it from an operational perspective: a laptop to type, software to edit, book printers that will talk to you, payment rails, and even access to world-class distribution: it’s all available to us now. On the other side of the market, students and teachers are not locked in either. Barriers t…
However, hard copy textbooks are still the dominant form in much of the developing world. We "technically literate" people often forget that we live in a bubble of our own making. A large percentage of students in the developing world simply do not have the means nor access to technology the way we do. They are dependent on low-cost printed textbooks to study and avail opportunities to get ahead in life.
The Textbook publishing industry is a cartel often pricing their offerings out-of-reach of economically disadvantaged students. Education and its prerequisite, access to textbooks, should be treated the same way we make available generic drugs in the pharmaceutical industry i.e. cheap/low-cost, decent quality offerings available to everybody. The prices of many of the textbooks is often eye-watering and that is why you have many low-cost textbook publishers in the developing world.
My main frustration is that most(all?) authors/professors are quite willing to forego any profits if it means they can get their textbooks into the hands of the students who need them. It is the publishing industry acting as the middleman and focused solely on profits which is ruining everything for everybody.