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

Share it with your friends Like

Thanks! Share it with your friends!


This is a combined slide/speaker video of Yoshua Bengio’s talk at NeurIPS 2019. Slide-synced non-YouTube version is here: https://slideslive.com/neurips/neurips-2019-west-exhibition-hall-c-b3-live

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:



Connect with on social media:
– Twitter: https://twitter.com/lexfridman
– LinkedIn: https://www.linkedin.com/in/lexfridman
– Facebook: https://www.facebook.com/lexfridman
– Instagram: https://www.instagram.com/lexfridman
– Medium: https://medium.com/@lexfridman


Lex Clips says:

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

Torsten Huenger says:

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.

Brando Miranda says:

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

Alessio Ansuini says:

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

Konan Jean-Claude Kouassi says:

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?

Immortal Discoveries says:

i just released all my AGI/evolution research, let me know your thoughts > https://groups.google.com/forum/#!topic/artificial-general-intelligence/U8-wPGwON_0

Tumisho Billson Mokgonyane says:

I was part of the #NeurIPS2019

Carlos Segura says:

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

jlee Lee says:

ML research by brain research ?

God Bennett says:

The scientific goal of the human species is probably to build Artificial General Intelligence.
Many more bright minds like Bengio's or Fridman will likely converge towards this endeavour:


Write a comment


Area 51