#85 Dr. Petar Veličković (Deepmind) - Categories, Graphs, Reasoning [NEURIPS22 UNPLUGGED]
Machine Learning Street Talk (MLST)
Neural Network Limitations and Extrapolation
This chapter explores the computational constraints of neural networks, emphasizing their challenges in representing infinite objects and the complexities of extrapolation versus interpolation. It discusses the alignment of neural network structures with target functions, the integration of different machine learning approaches, and ongoing research aimed at enhancing real-world applications.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
