NBDSM: Difference between revisions
No edit summary |
|||
| Line 1: | Line 1: | ||
== What == | == 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 | 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 [https://www.noisebridge.net/wiki/DreamTeam Noisebridge DreamTeam]. | ||
We're focused on theory. Implementation is | 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 learning, so our focus on it will be light. | ||
== Prerequisites == | == Prerequisites == | ||
| Line 21: | Line 21: | ||
*[https://calculatedcontent.com/ Calculated Content] | *[https://calculatedcontent.com/ Calculated Content] | ||
* the venerable [http://colah.github.io/ colah's blog] | * the venerable [http://colah.github.io/ colah's blog] | ||
== Papers == | |||
Good large scale overview of why the stat mech side is important | |||
Revision as of 20:01, 3 June 2017
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 learning, so our focus on it will be light.
Prerequisites
Our discussions are usually at graduate level in machine learning and theoretical physics. 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, and vector calculus (all of Stewart)
- 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
Papers
Good large scale overview of why the stat mech side is important