Study notebook

Press N to jot a timestamped note or B to pin a moment while watching.

Turing Lecture: Deep Learning for AI and System-2 Reasoning

Yoshua Bengio Association for Computing Machinery (ACM)

Full Professor, Université de Montréal & Mila Scientific Director

44:57·2018·undergraduate level·Conference Talk

Reviews distributed representations and attention mechanisms before proposing sparse, modular causal factor graphs for out-of-distribution generalization.

AI & ML Deep Learning Language Models & NLP Algorithms & Data Structures Apache Solr

Presented at Activate 2018

Slides: https://www.slideshare.net/lucidworks/deep-learning-for-ai-yoshua-bengio-mila

Discussion

0

Join the discussion — share questions, derivations, or timestamped notes.Sign in to comment

No comments on this lecture yet. Start the discussion above.

More from Yoshua Bengio

From System 1 to System 2 Deep Learning

MILA, Université de Montréal

Related lectures

Lecture 08: Architectures: Transformers (6.7960)

Phillip Isola · MIT

Shared subfield · Language Models & NLP & Deep Learning

Stanford CS25: V1 I Transformer Circuits, Induction Heads, In-Context Learning

Stanford Guest Researchers · Stanford University

Shared subfield · Language Models & NLP & Algorithms & Data Structures

Harvard CS50’s Artificial Intelligence with Python – Full University Course

Brian Yu · Harvard University

Shared subfield · Algorithms & Data Structures & Language Models & NLP

Large Language Models and Concepts in Natural Language

Ning Shi, David Basil · Alberta Machine Intelligence Institute (Amii)

Shared subfield · Language Models & NLP & Algorithms & Data Structures

POPRi: Private Federated Learning using Preference-Optimized Synthetic Data

Charlie Hou · Google Research & TechTalks

Shared subfield · Language Models & NLP & Algorithms & Data Structures

Building makemore Part 3: Activations, Gradients, Kaiming Init & BatchNorm

Andrej Karpathy · Eureka Labs

Shared subfield · Deep Learning & Language Models & NLP