Petar Veličković
Machine learning researcher focused on graph neural networks and geometric deep learning; contributes to the discussion on symmetries, permutation equivariance, and categorical generalizations.
Top 3 podcasts with Petar Veličković
Ranked by the Snipd community
134 snips
Dec 22, 2025 • 44min
Making deep learning perform real algorithms with Category Theory (Andrew Dudzik, Petar Velichkovich, Taco Cohen, Bruno Gavranović, Paul Lessard)
This discussion features Andrew Dudzik, a mathematician specializing in category theory; Taco Cohen, a researcher in geometric deep learning; and Petar Veličković, an expert in graph neural networks. They delve into why LLMs struggle with basic math by highlighting their pattern recognition flaws. The conversation proposes category theory as a framework to transition AI from trial-and-error towards a scientific approach. They explore concepts like equivariance, compositional structures, and the potential for unifying diverse machine learning perspectives.
64 snips
Sep 19, 2021 • 3h 33min
#60 Geometric Deep Learning Blueprint (Special Edition)
Joining the discussion are Petar Veličković from DeepMind, renowned for his work on graph neural networks, Taco Cohen from Qualcomm AI Research, specializing in geometric deep learning, and Joan Bruna, an influential figure in data science at NYU. They delve into geometric deep learning, exploring its foundations in symmetry and invariance. The conversation highlights innovative mathematical frameworks, the unification of geometries, and their implications in AI. Insights on dimensionality, algorithmic reasoning, and historical perspectives on geometry further enrich this engaging dialogue.
14 snips
Dec 8, 2022 • 37min
#85 Dr. Petar Veličković (Deepmind) - Categories, Graphs, Reasoning [NEURIPS22 UNPLUGGED]
Dr. Petar Veličković, a Staff Research Scientist at DeepMind known for his work on Graph Attention Networks, discusses fascinating advancements in deep learning. He explores how category theory enhances geometric deep learning and innovates graph neural networks. The conversation dives into algorithmic reasoning, exposing the shift from manual feature engineering to automated processes. Petar also addresses the challenges of neural networks with extrapolation versus interpolation and shares insights on expander graphs to overcome obstacles in information propagation.
