Connections between physics and deep learning

What people said

tedsanders · 2018-05 · Strong recommendation

Here's a related 2016 talk by Max Tegmark (second author) on connections between deep learning and physics: [VIDEO] The gist of it is that physical data tends to have symmetries, and these symmetries make descriptions of the data very compressible into relatively small neural circuits. Random data does not have this property, and cannot be learned easily. Super fascinating.

Read the original HN comment ↗

jonmc12 · 2017-01 · Recommendation

I think the argument for using physics models for constraints in a DL system was a more clear argument [VIDEO]

Read the original HN comment ↗

adityab · 2016-09 · Recommendation

You should watch Max Tegmark's talk "Connections between Physics and Deep Learning" if this interests you [1]. Additionally, a paper that has everyone excited about deep connections between the mathematical analysis of physical systems and the hierarchical feature learning paradigm speaks of the connection in terms of the Renormalization Group [2]. Regardless of it's practical utility, the philosophical implications do tickle the intellect. On a dreamy note, I wonder if it would be possible to draw Category-theoretic parallels between some physical theories and statistical learning theory. There is so much to learn, and I am trying my best to teach myself (on the side) the mathematics that they don't teach in my CS grad school. So much to learn, such little time. :) [1] [VIDEO] [2] [LINK]

Read the original HN comment ↗