Algorithmic Reasoning, Graph Neural Nets, AGI and Tips to researchers | Petar Veličković

Показать описание

Dr. Petar Veličković is a Staff Research Scientist at Googe DeepMind and an Affiliated lecturer at University of Cambridge. He is known for his research contributions in graph representation learning; particularly graph neural networks and graph attention networks. At DeepMind, he has been working on Neural Algorithmic Reasoning which we talk about more in this podcast. Petar’s research has featured in numerous media articles and been impactful in many ways including Google Map’s improved predictions.

Time stamps
00:00:00 Highlights
00:01:00 Introduction
00:01:50 Entry point in AI
00:03:44 Idea of Graph Attention Networks
00:06:50 Towards AGI
00:09:58 Attention in Deep learning
00:13:15 Attention vs Convolutions
00:20:20 Neural Algorithmic Reasoning (NAR)
00:25:40 End to end learning vs NAR
00:30:40 Improving Google Map predictions
00:34:08 Interpretability
00:41:28 Working at Google DeepMind
00:47:25 Fundamental vs Applied side of research
00:50:58 Industry vs Academia in AI research
00:54:25 Tips to young researchers
01:05:55 Is PhD required for AI research?

And his collection of invited talks: @petarvelickovic6033

About the Host:
Jay is a PhD student at Arizona State University.

Stay tuned for upcoming webinars!

***Disclaimer: The information contained in this video represents the views and opinions of the speaker and does not necessarily represent the views or opinions of any institution. It does not constitute an endorsement by any Institution or its affiliates of such video content.***

Рекомендации по теме

Комментарии

Petar is very humble and fun to listen to. Also, some really valuable tips for early-career researchers!

saliexplore

I am fortunate enough to have some personal interactions with Petar and always find what he says very inspiring and useful. It's always lovely to hear these fruitful conversation.

jjwilson

Algorithmic Reasoning, Graph Neural Nets, AGI and Tips to researchers | Petar Veličković

Neural Algorithmic Reasoning, Graph Neural Networks (GNNs), and the Path Towards Causal AI

Algorithmic Reasoning, Graph Neural Nets, AGI and Tips to researchers | Petar Veličković

Graph Neural Networks - a perspective from the ground up

Why Do Tree Based-Models Outperform Neural Nets on Tabular Data?

Graph Representation Learning for Algorithmic Reasoning

Petar Veličković: 'Reasoning on Natural Inputs'

Type-checking Graph Neural Networks (Dr. Petar Veličković)

Petar Veličković (DeepMind) — Neural Algorithmic Reasoning

NODES 2024 Best Of: GenAI

Graph Neural Networks are Dynamic Programmers

Tutorial: Neural Algorithmic Reasoning

How to explain Graph Neural Networks (with XAI)

Graph Networks in 2020

Model Stealing Attacks Against Inductive Graph Neural Networks

Joan Bruna: 'On Computational Hardness with Graph Neural Networks'

[CVPR 2020] SuperGlue: Learning Feature Matching with Graph Neural Networks (5min oral)

Learning and Extrapolation in Graph Neural Networks

Advanced Algorithms: Review-ETA Prediction with Graph Neural Networks in Google Maps

Exploring the Frontier of Graph Neural Networks Key Concepts, Architectures, and Trends

Introduction to graph neural networks (made easy!)

Graph Machine Learning for Visual Computing

Reducing communication in graph neural network training

Leveraging Graphs for AI

Causality and (Graph) Neural Networks