BI 105 Sanjeev Arora: Off the Convex Path

May 17, 2021 01:01:43
BI 105 Sanjeev Arora: Off the Convex Path
Brain Inspired
BI 105 Sanjeev Arora: Off the Convex Path

May 17 2021 | 01:01:43

/

Show Notes

Sanjeev and I discuss some of the progress toward understanding how deep learning works, specially under previous assumptions it wouldn’t or shouldn’t work as well as it does. Deep learning theory poses a challenge for mathematics, because its methods aren’t rooted in mathematical theory and therefore are a “black box” for math to open. We discuss how Sanjeev thinks optimization, the common framework for thinking of how deep nets learn, is the wrong approach. Instead, a promising alternative focuses on the learning trajectories that occur as a result of different learning algorithms. We discuss two examples of his research to illustrate this: creating deep nets with infinitely large layers (and the networks still find solutions among the infinite possible solutions!), and massively increasing the learning rate during training (the opposite of accepted wisdom, and yet, again, the network finds solutions!). We also discuss his past focus on computational complexity and how he doesn’t share the current neuroscience optimism comparing brains to deep nets.

Timestamps
0:00 – Intro
7:32 – Computational complexity
12:25 – Algorithms
13:45 – Deep learning vs. traditional optimization
17:01 – Evolving view of deep learning
18:33 – Reproducibility crisis in AI?
21:12 – Surprising effectiveness of deep learning
27:50 – “Optimization” isn’t the right framework
30:08 – Infinitely wide nets
35:41 – Exponential learning rates
42:39 – Data as the next frontier
44:12 – Neuroscience and AI differences
47:13 – Focus on algorithms, architecture, and objective functions
55:50 – Advice for deep learning theorists
58:05 – Decoding minds

Other Episodes

Episode 0

June 24, 2020 01:16:03
Episode Cover

BI 075 Jim DiCarlo: Reverse Engineering Vision

Jim and I discuss his reverse engineering approach to visual intelligence, using deep models optimized to perform object recognition tasks. We talk about the...

Listen

Episode 0

October 25, 2018 00:49:34
Episode Cover

BI 015 Terrence Sejnowski: How to Start a Deep Learning Revolution

Show notes: His new book, The Deep Learning Revolution: His Computational Neurobiology Laboratory at the Salk Institute. His faculty page at UCSD. His first...

Listen

Episode 0

February 07, 2023 01:28:39
Episode Cover

BI 160 Ole Jensen: Rhythms of Cognition

Support the show to get full episodes and join the Discord community. Check out my free video series about what's missing in AI and...

Listen