Published Mar 25, 2022

#71 - ZAK JOST (Graph Neural Networks + Geometric DL) [UNPLUGGED]

Research scientist Zach Jost delves into the intricacies of graph neural networks, discussing their foundational concepts, unique advantages, and his innovative course designed to foster collaborative and practical learning. The episode also highlights the role of theoretical geometric deep learning frameworks in advancing neural network architectures for complex data processing.

Episode Highlights

Topics covered

Episode Highlights

Related Episodes

WelcomeAIOverlords (Zak Jost)
Answers 383 questions
#82 - Dr. JOSCHA BACH - Digital Physics, DL and Consciousness [UNPLUGGED]
Answers 383 questions
#60 Geometric Deep Learning Blueprint (Special Edition)
Answers 383 questions
#66 ALEXANDER MATTICK - [Unplugged / Community Edition]
Answers 383 questions
#65 Prof. PEDRO DOMINGOS [Unplugged]
Answers 383 questions
#063 - Prof. YOSHUA BENGIO - GFlowNets, Consciousness & Causality
Answers 383 questions
Jürgen Schmidhuber - Neural and Non-Neural AI, Reasoning, Transformers, and LSTMs
Answers 383 questions
#85 Dr. Petar Veličković (Deepmind) - Categories, Graphs, Reasoning [NEURIPS22 UNPLUGGED]
Answers 383 questions
#53 Quantum Natural Language Processing - Prof. Bob Coecke (Oxford)
Answers 383 questions
#72 Prof. KEN STANLEY 2.0 - On Art and Subjectivity [UNPLUGGED]
Answers 383 questions
#49 - Meta-Gradients in RL - Dr. Tom Zahavy (DeepMind)
Answers 383 questions
Dr. Paul Lessard - Categorical/Structured Deep Learning
Answers 383 questions
Robert Lange on NN Pruning and Collective Intelligence
Answers 383 questions
ICLR 2020: Yoshua Bengio and the Nature of Consciousness
Answers 383 questions
#041 - Biologically Plausible Neural Networks - Dr. Simon Stringer
Answers 383 questions

Dexa/Machine Learning Street Talk (MLST)

#71 - ZAK JOST (Graph Neural Networks + Geometric DL) [UNPLUGGED]

Topics covered

Popular Clips

Graph Convolution Networks

Transformers vs GNNs

Graph Wavelets in ML

Graph Neural Networks

Neural Network Insights

Graph Representation Insights

Symmetry in Graphs

Message Passing Insights

Machine Learning Course

Geometric Deep Learning Blueprint

Community, Deadlines

Graph Rewiring

Graph Neural Networks

Graph Neural Networks

Episode Highlights

Graph Neural Networks

Zak's GNN Course

Geometric Deep Learning

Related Episodes

WelcomeAIOverlords (Zak Jost)

#82 - Dr. JOSCHA BACH - Digital Physics, DL and Consciousness [UNPLUGGED]

#60 Geometric Deep Learning Blueprint (Special Edition)

#66 ALEXANDER MATTICK - [Unplugged / Community Edition]

#65 Prof. PEDRO DOMINGOS [Unplugged]

#063 - Prof. YOSHUA BENGIO - GFlowNets, Consciousness & Causality

Jürgen Schmidhuber - Neural and Non-Neural AI, Reasoning, Transformers, and LSTMs

#85 Dr. Petar Veličković (Deepmind) - Categories, Graphs, Reasoning [NEURIPS22 UNPLUGGED]

#53 Quantum Natural Language Processing - Prof. Bob Coecke (Oxford)

#72 Prof. KEN STANLEY 2.0 - On Art and Subjectivity [UNPLUGGED]

#49 - Meta-Gradients in RL - Dr. Tom Zahavy (DeepMind)

Dr. Paul Lessard - Categorical/Structured Deep Learning

Robert Lange on NN Pruning and Collective Intelligence

ICLR 2020: Yoshua Bengio and the Nature of Consciousness

#041 - Biologically Plausible Neural Networks - Dr. Simon Stringer

#71 - ZAK JOST (Graph Neural Networks + Geometric DL) [UNPLUGGED]

Topics covered

Popular Clips

Episode Highlights

Graph Neural NetworksZach Jost, a research scientist at Amazon, explores the foundational concepts and challenges of graph neural networks (GNNs). He discusses their unique advantages over other neural networks and innovative solutions to common issues like over-squashing.

Graph Neural Networks

Zak's GNN CourseZach Jost introduces his innovative course on Graph Neural Networks, blending theoretical insights with practical applications. The course fosters a collaborative learning environment, emphasizing community engagement and hands-on experience.

Zak's GNN Course

Geometric Deep LearningTheoretical frameworks in geometric deep learning provide insights into neural network architectures through symmetry and transformations. These principles are applied in graph convolutional networks, enabling efficient processing of complex graph data.

Geometric Deep Learning

Related Episodes