NBDSM: Difference between revisions
(→Papers) |
(→Books) |
||
Line 74: | Line 74: | ||
* [https://libgen.unblocked.srl/book/index.php?md5=AFEE8F3BEF62DC5C7A191451259AD8EB Engel - Statistical Mechanics of Learning] I haven't looked at this yet, but it seems promising. | * [https://libgen.unblocked.srl/book/index.php?md5=AFEE8F3BEF62DC5C7A191451259AD8EB Engel - Statistical Mechanics of Learning] I haven't looked at this yet, but it seems promising. | ||
* [http://www.inference.org.uk/itila/p0.html MacKay - Information Theory, Inference, and Learning Algorithms] Link [https://libgen.unblocked.srl/book/index.php?md5=E70CC484C7FF51073859B15779162C25 here] | * [http://www.inference.org.uk/itila/p0.html MacKay - Information Theory, Inference, and Learning Algorithms] Link [https://libgen.unblocked.srl/book/index.php?md5=E70CC484C7FF51073859B15779162C25 here] | ||
* [https://libgen.unblocked.pub/book/index.php?md5=4CFDD37EEDB946D6E944750F746DB72B Bishop - Pattern Recognition and Machine Learning] Great pedagogical introduction to the basics. | * [https://libgen.unblocked.pub/book/index.php?md5=4CFDD37EEDB946D6E944750F746DB72B Bishop - Pattern Recognition and Machine Learning] Great pedagogical introduction to the basics. Good treatment of exponential family. | ||
* [https://libgen.unblocked.srl/book/index.php?md5=E4B2AB0EF22458F94C835D4D2397034E Goodfellow et al. - Deep Learning] | * [https://libgen.unblocked.srl/book/index.php?md5=E4B2AB0EF22458F94C835D4D2397034E Goodfellow et al. - Deep Learning] | ||
* [https://libgen.unblocked.srl/book/index.php?md5=3E76F8F5189A047550CA9020D97848E4 Mezard - Information, Physics, and Computation] | * [https://libgen.unblocked.srl/book/index.php?md5=3E76F8F5189A047550CA9020D97848E4 Mezard - Information, Physics, and Computation] |
Revision as of 12:24, 20 July 2017
Schedule
7/6/17 - Talk and Discussion: Steve Young - Boltzmann Machines and Statistical Mechanics.
PREREADINGS:
MacKay - Information Theory, Inference, and Learning Algorithms Chapter 43 on the Boltzmann machine. Chapter 42 on Hopfield networks.
Media:hinton_lect11.pdf Media:hinton_lect12.pdf Lecture notes from Hinton's Coursera class. Good overview of Boltzmann machines and Hopfield nets. You can sign up for the free course and watch the accompanying videos here. They're also on Youtube.
What
nBDSM is the noiseBridge Deepnet and Statistical Mechanics working group. We meet weekly to learn, teach, and discuss topics at the intersection of AI/deep learning and statistical mechanics. Note that we have a non-trivial overlap with The One, The Only Noisebridge DreamTeam.
We're focused on theory. Implementation is fun too, but has its own set of (mostly orthogonal) skills that we'll cover only lightly.
Prerequisites
Our discussions are at upper division to grad level in machine learning and statistical mechanics. To be able to get something out of them, you should know
- linear algebra (at the level of D. Lay's book)
- single and multi-variable calculus, vector calculus, Lagrange multiplers, Taylor expansions (all of Stewart's textbook).
- basics of statistics, including bayesian
- statistical mechanics (at the level of McGreevy's MIT lecture notes)
There are plenty of other places to learn this stuff. Eg you can review your probability, stats and linear algebra from chapters 2 and 3 of Goodfellow.
Links
Check out these cool links
- A great talk by Ganguli at last year's deep learning summer school in Montreal.
- Anything recent by Ganguli at the Neural Dynamics and Computation Lab as well.
- Calculated Content
- The venerable colah's blog
- Stat Mech//Machine Learning conference 2017 at Berkeley: smml:2017
- Proceedings of the Les Houches 2013 school on Statistical physics, Optimization, Inference and Message-Passing algorithms. Fairly advanced.
- Videos from Geoff Hinton's neural net course on Coursera.
- A blog post about exponential families that demonstrates the sort of intuition we're trying to build.
- Media:maxEntChap10.pdf Intro to principle of Maximum Entropy
Papers
Overviews
Good large scale overview of why the stat mech side is important
- Advani et al. - Stat mech of complex neural systems and high dimensional data - arXiv:1301.7115v1
Less emphasis on the physics, more emphasis on the stat mech <-> statistical inference connection.
- Mastromatteo - On the typical properties of inverse problems in stat mech - arXiv:1311.0910v1
- Zdeborová et al. - arXiv:1511.02476
Interesting papers
- Chen et al. - On the Equivalence of Restricted Boltzmann Machines and Tensor Network States - arXiv:1701:04831v1
- Mehta et al. - An exact mapping between the Variational Renormalization Group and Deep Learning - arXiv:1410.3831
- Saxe et al. - Exact solutions to the nonlinear dynamics of learning in deep linear neural networks - arXiv:1312.6120
Unreasonably Interesting papers
- Gan et al. - Holography as Deep Learning - arXiv:1705.05750 (NB: This of course is the real reason I started this meetup.)
Books
IMPORTANT NOTICE ON PIRACY
- A great place to find books and articles is Library Genesis. I use these links for books and articles: [1], [2].
Stat Mech
- Huang's text is the bronze standard for grad level stat mech.
- Chandler's text is supposedly great for stat mech, although I haven't read it.
Stat Mech and Stat Inference
- Engel - Statistical Mechanics of Learning I haven't looked at this yet, but it seems promising.
- MacKay - Information Theory, Inference, and Learning Algorithms Link here
- Bishop - Pattern Recognition and Machine Learning Great pedagogical introduction to the basics. Good treatment of exponential family.
- Goodfellow et al. - Deep Learning
- Mezard - Information, Physics, and Computation
- Jaynes - Probability Theory, The Logic of Science An excellent introduction to Bayesian reasoning and probability theory in general, from a very pedagogical, opinionated point-of-view. Dives into the motivations behind some information theory as well.
Ideas for future talks
Here's some ideas for future talks. If you want to present one of these,
A) Feel free to be advanced as you like -- assume an audience of graduate students.
but
B) Don't feel pressured to go any faster than you want. If you think you can give a pedagogical 'for dummies' talk in the course of an hour and a half, go for it!
- Derive capacity of Hopfield net and understand this limitation intuitively
- Explain similarity/relationship/identity of Bayesian inference and maximum entropy formalism.
- Deep intuitive dive on Lagrangian duals and what they really do/mean in the context of statistical inference/machine learning/stat mech