The Videos are copyrighted to YouTube and the author. The videos are reproduced here for the easy access by the viewers.
Today we’re joined by Sophia Sanborn, a postdoctoral scholar at the University of California, Santa Barbara. In our conversation with Sophia, we explore the concept of universality between neural representations and deep neural networks, and how these principles of efficiency provide an ability to find consistent features across networks and tasks. We also discuss her recent paper on Bispectral Neural Networks which focuses on Fourier transform and its relation to group theory, the implementation of bi-spectral spectrum in achieving invariance in deep neural networks, the expansion of geometric deep learning on the concept of CNNs from other domains, the similarities in the fundamental structure of artificial neural networks and biological neural networks and how applying similar constraints leads to the convergence of their solutions.
🔔 Subscribe to our channel for more great content just like this: https://youtube.com/twimlai?sub_confirmation=1
🗣️ CONNECT WITH US!
===============================
Subscribe to the TWIML AI Podcast: https://twimlai.com/podcast/twimlai/
Join our Slack Community: https://twimlai.com/community/
Subscribe to our newsletter: https://twimlai.com/newsletter/
Want to get in touch? Send us a message: https://twimlai.com/contact/
📖 CHAPTERS
===============================
00:00:56 – Background
00:07:00 – Efficient coding as the guiding principle to constrain representation learning
00:13:20 – Universality between artificial neural networks and biological neural networks
00:19:22 – Fourier transform and its relation to group theory and Bispectral Neural Network paper
00:29:57 – Fourier transform is equivariant
00:34:44 – Emerging geometric deep learning techniques
00:39:47 – Trade-off between internal network complexity, data complexity, and training time complexity
00:42:16 – Geometric structure is essential for accurate and efficient machine learning
00:45:27 – Artificial and biological neural networks share a similar fundamental structure
🔗 LINKS & RESOURCES
===============================
Bispectral Neural Networks – https://arxiv.org/abs/2209.03416
For a complete list of references, head over to https://twimlai.com/go/644.
📸 Camera: https://amzn.to/3TQ3zsg
🎙️Microphone: https://amzn.to/3t5zXeV
🚦Lights: https://amzn.to/3TQlX49
🎛️ Audio Interface: https://amzn.to/3TVFAIq
🎚️ Stream Deck: https://amzn.to/3zzm7F5
source