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

59:04
 
Chia sẻ
 

Manage episode 306907105 series 2355587
Thông tin tác giả TWIML and Sam Charrington được phát hiện bởi Player FM và cộng đồng của chúng tôi - bản quyền thuộc sở hữu của nhà sản xuất (publisher), không thuộc về Player FM, và audio được phát trực tiếp từ máy chủ của họ. Bạn chỉ cần nhấn nút Theo dõi (Subscribe) để nhận thông tin cập nhật từ Player FM, hoặc dán URL feed vào các ứng dụng podcast khác.

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

573 tập