Future of Algorithmic Reasoning
Petar discusses the integration of large-scale models with algorithmic reasoning, emphasizing the need for a convergence of concepts and execution. He envisions a future where models can seamlessly combine perceptual components with graph neural networks for enhanced problem-solving capabilities.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#85 Dr. Petar Veličković (Deepmind) - Categories, Graphs, Reasoning [NEURIPS22 UNPLUGGED]
Related Questions