# NBDSM

## Contents

# UPDATE: FIRST MEETUP 7/6/17 AT 7PM

Our first meetup will be July 6th at 7pm, at Noisebridge Hackerspace, 2169 Mission st. San Francisco.

I'll talk about some of the key ideas at the intersection of stat mech and AI, in the context of what's known as the Boltzmann machine. A specialized version of this -- the restricted Boltzmann machine (RBM) -- an AI architecture partially behind the resurgence of interest in neural networks in the late aughts, prompted by Geoff Hinton "figuring out how to make them 10,000 times faster" via a procedure known as contrastive divergence. A significant amount of the buzz today in deep learning came from this development.

Some concepts to (hopefully re) acquaint yourselves with before the first meeting: Ising Model, partition function, thermodynamic equilibrium, Lagrange multipliers (and Lagrangian dual), Bayesian inference, global versus local extrema, simulated annealing.

Please try to

- be on top of the prerequisites (below)
- watch/look at all the links (also below)
- skim the papers below (most importantly: read the abstract, introduction and conclusions, slowly. look up words you don't understand, try to connect what they seem to be talking about with what you already know. Research is ALL about throwing yourself into stuff you don't understand, and learning by exposure.)

But if you can't, come anyway!

## SCHEDULE

- 7/6/17 - Steve Young, PhD -- Boltzmann Machines and Statistical Mechanics.

PREREADINGS: MacKay - Information Theory, Inference, and Learning Algorithms Chapter 43 on the Boltzmann machine. Chapter 42 on Hopfield networks.

## 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 skills that are mostly orthogonal to what we'll be covering, so our focus on it will be light.

## Prerequisites

Our discussions are ~at upper division to graduate level in machine learning and statistical mechanics. To be able to get something out of them, you should have at least undergrad proficiency in

- 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).
- statistics, including bayesian
- statistical mechanics (at the level of McGreevy's MIT lecture notes)

## Links

Here are some cool links (you can use these to figure out what to study to get up to speed)

- 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
- Les Houches 2013 school on Statistical physics, Optimization, Inference and Message-Passing algorithms. Contains links to papers/talks.

## Papers

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

## Books

- A great place to find books and articles is Library Genesis. I use these links for books and articles: [1], [2].
- Huang's text is a standard for grad level stat mech.
- 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