The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

The Benefit of Bottlenecks in Evolving Artificial Intelligence with David Ha - #535

Nov 11, 2021

David Ha, a research scientist at Google Brain, shares his insights on how constraints and biological bottlenecks can revolutionize AI training. He discusses the evolution of generative adversarial networks, highlighting their journey from basic image generation to sophisticated applications. The conversation dives into neuroevolution, sensory substitution, and adaptive learning techniques, showcasing how these innovations can enhance AI systems. David also explores the importance of collective intelligence and self-organization in neural networks, making profound connections to both biology and technology.

59:04

Creator website

Episode guests

David Ha

AI Chapters

Episode notes

Intro

2min

From Finance to AI: A Journey of Discovery

6min

Advancements in GANs and Reinforcement Learning

22min

Evolving Intelligence: Neural Networks and Evolutionary Algorithms

13min

Exploring Sensory Substitution and Its Impact on Perception

3min

Adaptive Learning with Permutation Invariant Networks

9min

Exploring Collective Intelligence and Self-Organization in Machine Learning

4min

Today we’re joined by David Ha, a research scientist at Google.

In nature, there are many examples of “bottlenecks”, or constraints, that have shaped our development as a species. Building upon this idea, David posits that these same evolutionary bottlenecks could work when training neural network models as well. In our conversation with David, we cover a TON of ground, including the aforementioned biological inspiration for his work, then digging deeper into the different types of constraints he’s applied to ML systems. We explore abstract generative models and how advanced training agents inside of generative models has become, and quite a few papers including Neuroevolution of self-interpretable agents, World Models and Attention for Reinforcement Learning, and The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning.

This interview is Nerd Alert certified, so get your notes ready!

PS. David is one of our favorite follows on Twitter (@hardmaru), so check him out and share your thoughts on this interview and his work!

The complete show notes for this episode can be found at twimlai.com/go/535

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.

Get the app