Yoshua Bengio: From System 1 Deep Learning to System 2 Deep Learning (NeurIPS 2019)

preview_player
Показать описание

This is a clip on the Lex Clips channel that I mostly use to post video clips from the Artificial Intelligence podcast, but occasionally I post clips from other lectures by me or others. Hope you find these interesting, thought-provoking, and inspiring. If you do, please subscribe, click bell icon, and share.

Lex Clips channel:

Lex Fridman channel:

Artificial Intelligence podcast website:

Apple Podcasts:

Spotify:

RSS:

Connect with on social media:
  1. Lex Clips
  2. neurips
  3. nips
  4. deep learning
  5. machine learning
Рекомендации по теме
Yoshua Bengio: From 0:55:03

Yoshua Bengio: From System 1 Deep Learning to System 2 Deep Learning (NeurIPS 2019)

Yoshua Bengio | 0:56:36

Yoshua Bengio | From System 1 Deep Learning to System 2 Deep Learning | NeurIPS 2019

Prof. Yoshua Bengio 0:55:03

Prof. Yoshua Bengio | From System 1 Deep Learning to System 2 Deep Learning | NeurIPS 2019

Yoshua Bengio From 0:01:41

Yoshua Bengio From System 1 Deep Learning to System 2 Deep Learning

The Rise of 0:17:54

The Rise of Artificial Intelligence through Deep Learning | Yoshua Bengio | TEDxMontreal

Yoshua Bengio: Attention 0:08:56

Yoshua Bengio: Attention and Consciousness (NeurIPS 2019)

[SAIF 2020] Day 0:20:30

[SAIF 2020] Day 1: Towards Discovering Casual Representations - Yoshua Bengio | Samsung

Yoshua Bengio – 0:19:31

Yoshua Bengio – Deep Learning for AI

We’ve PASSED The 0:00:14

We’ve PASSED The Turing Test | Yoshua Bengio

How has Deep 0:05:19

How has Deep Learning Developed in 2019 - Yoshua Bengio (1/4)

Learning to Understand 0:39:18

Learning to Understand Language: Text Corpora are not Enough | Yoshua Bengio

Yoshua Bengio: System 0:29:46

Yoshua Bengio: System 2 GFlowNets: Induction Biases Towards Machines that Understand and Think

Neural backpropagation workshop 0:59:21

Neural backpropagation workshop 2019 - Yoshua Bengio

Deep Learning for 0:30:33

Deep Learning for AI, Yoshua Bengio

IIT Madras- CCBR- 0:55:55

IIT Madras- CCBR- Prof Yoshua Bengio -“Towards biologically plausible deep learning”

Yoshua Bengio: Deep 0:59:13

Yoshua Bengio: Deep Learning Cognition | Full Keynote - AI in 2020 & Beyond

David Cox and 0:17:24

David Cox and Yoshua Bengio Fireside Chat

Building AGI: Promising 0:38:42

Building AGI: Promising Approaches, Remaining Milestones, and Likely Obstacles | Yoshua Bengio

Yoshua Bengio – 1:10:34

Yoshua Bengio – Cognitively-inspired inductive biases for higher-level cognition

Yoshua Bengio: What 0:01:32

Yoshua Bengio: What is Currently Missing in Deep Learning (NeurIPS 2019)

Yoshua Bengio: Deep 0:42:19

Yoshua Bengio: Deep Learning | Lex Fridman Podcast #4

Creating Human-Level AI 0:30:40

Creating Human-Level AI | Yoshua Bengio

DLRL Summer School 1:47:30

DLRL Summer School 2023 - Yoshua Bengio - Machine Learning for Scientific Discovery & AI Safety

Deep Learning, part 1:37:07

Deep Learning, part 1 - Yoshua Bengio - MLSS 2020, Tübingen

Комментарии
Автор

Outline of the talk:
0:00 - Introduction
0:56 - The State of Deep Learning
2:20 - System 1 and System 2
4:09 - What's currently missing in deep learning
8:56 - Out-of-distribution generalization
12:16 - Compositionality
16:08 - Contrast with Symbolic AI
18:11 - Attention and Consciousness
27:07 - Consciousness prior
32:17 - Meta-learning
39:09 - Operating on sets of objects
41:21 - Recap
44:48 - Question: moral implications of building machines that are conscious
46:18 - Question: Integrated information theory
47:17 - Question: Spatial prior
48:28 - Question: Symbolic AI
50:51 - Question: What is a data distribution?
52:05 - Question: measuring progress
52:52 - Question: causality
53:34 - Question: relation and associative memory

LexClips
Автор

I am so glad I found this video. The presenter gives rise to various useful points!

carlossegura
Автор

I was there, and after 8 months I am still studying what he said...

ans
Автор

It seems to me like there should be a way to run proof searches where you are constrained to converge to logical proofs but you allow a pre-trained intuitive neural network to make the decisions about which paths to explore first.

Another idea is some non-symmetric adversarial system where one half of the system is optimizing to imitate human creativity and the other system is optimizing for logical correctness. A left brain/right brain system.

fennecbesixdouze
Автор

What is the main argument professor Bengio has against hybrid systems (DL + Symbolic AI)?

brandomiranda
Автор

Thank you very much Professor for a so bright talk.
Just a question : the System 2 Deep Learning architecture showed is very similar to the Bayesian network Open-universe Probability Model - OUPM (section 14.6.3 of the book of Russell and Norvig: Artificial Intelligence, a modern approach). Is possible to elaborate about the difference, please?

kkjc
Автор

Dual-system theories are popular in psychology but highly disputed. Kahneman may have received recognition for research related to System 1 (heuristics and habitual responses). What is disputed, however, is System 2. Is a System 2 necessary to explain human "higher" cognition. It is probably a bad idea to base your AI ideas on this flawed idea from psychology.

torstenhuenger