Neural Network Depth
Joan delves into the importance of depth in neural networks and the necessity of incorporating invariances to improve learning efficiency. Understanding the role of symmetries in architecture design and the need for additional prior information beyond just invariants are key takeaways from this discussion.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#60 Geometric Deep Learning Blueprint (Special Edition)
Related Questions
What are more examples of admissible sets of functions in the context of neural network architectures, as discussed in the episode Vladimir Vapnik: Statistical Learning | Lex Fridman Podcast #5 and the clip Understanding Invariance, as well as in the episode Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence | Lex Fridman Podcast #71 and the clip Function Sets and Invariants?
What are more examples of admissible sets of functions in the context of neural network architectures as discussed in the episode Vladimir Vapnik: Statistical Learning | Lex Fridman Podcast #5 and the clip Understanding Invariance?