Pre-Debate Material :
Meta transfer learning for factorizing representations and knowledge for AI - Yoshua Bengio : https://youtu.be/CHnJYBpMjNY
#AIDebate #MontrealAI
Meta transfer learning for factorizing representations and knowledge for AI - Yoshua Bengio : https://youtu.be/CHnJYBpMjNY
#AIDebate #MontrealAI
YouTube
Meta transfer learning for factorizing representations and knowledge for AI - Yoshua Bengio
Speaker: Yoshua Bengio
Title: Meta transfer learning for factorizing representations and knowledge for AI
Abstract:
Whereas machine learning theory has focused on generalization to examples from the same distribution as the training data, better understanding…
Title: Meta transfer learning for factorizing representations and knowledge for AI
Abstract:
Whereas machine learning theory has focused on generalization to examples from the same distribution as the training data, better understanding…
Pre-Debate Material :
WSAI Americas 2019 - Yoshua Bengio - Moving beyond supervised deep learning : https://youtu.be/0GsZ_LN9B24
#AIDebate #MontrealAI
WSAI Americas 2019 - Yoshua Bengio - Moving beyond supervised deep learning : https://youtu.be/0GsZ_LN9B24
#AIDebate #MontrealAI
YouTube
WSAI Americas 2019 - Yoshua Bengio - Moving beyond supervised deep learning
Moving beyond supervised deep learning
Watch Yoshua Bengio, Professor of Computer Science and Operations Research at Université de Montréal on stage at World Summit AI Americas 2019. americas.worldsummit.ai
Watch Yoshua Bengio, Professor of Computer Science and Operations Research at Université de Montréal on stage at World Summit AI Americas 2019. americas.worldsummit.ai
Pre-Debate Material :
"BabyAI: First Steps Towards Grounded Language Learning With a Human In the Loop"
Maxime Chevalier-Boisvert et al.:
https://arxiv.org/abs/1810.08272v2
#AIDebate #MontrealAI #ReinforcementLearning
"BabyAI: First Steps Towards Grounded Language Learning With a Human In the Loop"
Maxime Chevalier-Boisvert et al.:
https://arxiv.org/abs/1810.08272v2
#AIDebate #MontrealAI #ReinforcementLearning
Pre-Debate Material
"Deep Learning was great, what's next?"
What is missing to extend Deep Learning to reach human-level AI? Yoshua Bengio : https://youtu.be/cBt5EvHRS5M?t=70
RSVP (2320 people already signed up) at https://bengio-marcus.eventbrite.ca
#AIDebate #ArtificialIntelligence #DeepLearning
"Deep Learning was great, what's next?"
What is missing to extend Deep Learning to reach human-level AI? Yoshua Bengio : https://youtu.be/cBt5EvHRS5M?t=70
RSVP (2320 people already signed up) at https://bengio-marcus.eventbrite.ca
#AIDebate #ArtificialIntelligence #DeepLearning
YouTube
"Deep Learning was great, what's next?" - Yoshua Bengio (2/4)
Interested in attending a RE•WORK Summit? Get 25% off your pass from December 2-6! See the list of summits here - https://bit.ly/2DrrCbj "Deep Learning was g...
Pre-Debate Material
From System 1 Deep Learning to System 2 Deep Learning
Wed Dec 11th 02:15 -- 03:05 PM PT, live streamed from NeurIPS
Yoshua Bengio https://neurips.cc/Conferences/2019/Schedule?showEvent=15488
#AIDebate
From System 1 Deep Learning to System 2 Deep Learning
Wed Dec 11th 02:15 -- 03:05 PM PT, live streamed from NeurIPS
Yoshua Bengio https://neurips.cc/Conferences/2019/Schedule?showEvent=15488
#AIDebate
Pre-Debate Material
"Making the Mind"
Why we've misunderstood the nature-nurture debate.
GARY MARCUS : http://bostonreview.net/books-ideas/gary-marcus-making-mind
#AIDebate
"Making the Mind"
Why we've misunderstood the nature-nurture debate.
GARY MARCUS : http://bostonreview.net/books-ideas/gary-marcus-making-mind
#AIDebate
Boston Review
Making the Mind
Why we've misunderstood the nature-nurture debate.
Pre-Debate Material
"The Consciousness Prior"
Yoshua Bengio : https://arxiv.org/abs/1709.08568
#DeepLearning #ArtificialIntelligence #AIDebate
"The Consciousness Prior"
Yoshua Bengio : https://arxiv.org/abs/1709.08568
#DeepLearning #ArtificialIntelligence #AIDebate
Learning Neural Causal Models from Unknown Interventions
Ke et al.: https://arxiv.org/abs/1910.01075
#AIDebate #MachineLearning #ArtificialIntelligence
Ke et al.: https://arxiv.org/abs/1910.01075
#AIDebate #MachineLearning #ArtificialIntelligence
arXiv.org
Learning Neural Causal Models from Unknown Interventions
Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data. However, there are theoretical...
Bengio-Marcus AI Debate Post Mortem, Part I: The Deep Learning Pivot
Gary Marcus : https://medium.com/@GaryMarcus/bengio-marcus-ai-debate-post-mortem-part-i-the-deep-learning-pivot-f7bd62b9861c
#AIDebate
Gary Marcus : https://medium.com/@GaryMarcus/bengio-marcus-ai-debate-post-mortem-part-i-the-deep-learning-pivot-f7bd62b9861c
#AIDebate
Medium
Bengio-Marcus AI Debate Post Mortem, Part I: The Deep Learning Pivot
important update, December 29, 2019: the piece below apparently led some people to think I was challenging Yoshua’s integrity.
After AI Debate Readings
"Recurrent Independent Mechanisms"
Goyal et al., 2019: https://arxiv.org/abs/1909.10893
#AIDebate
"Recurrent Independent Mechanisms"
Goyal et al., 2019: https://arxiv.org/abs/1909.10893
#AIDebate
After AI Debate Reading
Rule learning by seven-month-old infants
G. F. Marcus et al., Science 283(5398):77-80, February 1999 : https://www.researchgate.net/publication/13415195_Rule_learning_by_seven-month-old_infants
#AIDebate
Rule learning by seven-month-old infants
G. F. Marcus et al., Science 283(5398):77-80, February 1999 : https://www.researchgate.net/publication/13415195_Rule_learning_by_seven-month-old_infants
#AIDebate
ResearchGate
(PDF) Rule learning by seven-month-old infants
PDF | A fundamental task of language acquisition is to extract abstract algebraic rules. Three experiments show that 7-month-old infants attend longer... | Find, read and cite all the research you need on ResearchGate
The AI field is in its infancy
A great definition of deep learning would allow the field to be more welcoming, to extend its reach to other fields and to illuminate the state of discourse. #AIDebate
A great definition of deep learning would allow the field to be more welcoming, to extend its reach to other fields and to illuminate the state of discourse. #AIDebate
"Deep learning, science, engineering, research, and terminology"
A Dialogue between Yoshua Bengio and Gary Marcus : https://medium.com/@GaryMarcus/deep-learning-science-engineering-research-and-terminology-292a747a94d3
#AIDebate
A Dialogue between Yoshua Bengio and Gary Marcus : https://medium.com/@GaryMarcus/deep-learning-science-engineering-research-and-terminology-292a747a94d3
#AIDebate
Medium
Deep learning, science, engineering, research, and terminology
A Dialogue between Yoshua Bengio and Gary Marcus
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
Mao et al.: https://arxiv.org/abs/1904.12584
#ArtificialIntelligence #NeuroSymbolic #AIDebate
Mao et al.: https://arxiv.org/abs/1904.12584
#ArtificialIntelligence #NeuroSymbolic #AIDebate
Differentiable Reasoning on Large Knowledge Bases and Natural Language
Minervini et al.: https://arxiv.org/abs/1912.10824
Open-source neuro-symbolic reasoning framework, in TensorFlow: https://github.com/uclnlp/gntp
#AIDebate #NeuroSymbolic #Reasoning
Minervini et al.: https://arxiv.org/abs/1912.10824
Open-source neuro-symbolic reasoning framework, in TensorFlow: https://github.com/uclnlp/gntp
#AIDebate #NeuroSymbolic #Reasoning
GitHub
uclnlp/gntp
Contribute to uclnlp/gntp development by creating an account on GitHub.
Nobel prize winner Danny Kahneman cited Gary Marcus (see the recent #AIdebate) and the need for hybrid models in science/AI (including reasoning and logic, in addition to learning), when referring to his systems 1 and 2 (see Thinking Fast and Slow). Neural-symbolic computing is a foundation for this line of research. #AAAI2020 congratulations to Francesca Rossi for the panel with Kahneman and the Turing Award winners. https://link.springer.com/book/10.1007/978-3-540-73246-4
SpringerLink
Neural-Symbolic Cognitive Reasoning
Humans are often extraordinary at performing practical reasoning. There are cases where the human computer, slow as it is, is faster than any artificial intelligence system. Are we faster because of the way we perceive knowledge as opposed to the way we represent…
"absolutely brilliant"
—Nobel Laureate Danny Kahneman
The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
Gary Marcus: https://arxiv.org/abs/2002.06177
#AIDebate #DeepLearning #RobustAI
—Nobel Laureate Danny Kahneman
The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
Gary Marcus: https://arxiv.org/abs/2002.06177
#AIDebate #DeepLearning #RobustAI
Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective
Luis Lamb et al.: https://arxiv.org/abs/2003.00330
#aidebate #thinkingfastandslow #AAAI2020debate #neurosymbolic #neurosymboliccomputing
Luis Lamb et al.: https://arxiv.org/abs/2003.00330
#aidebate #thinkingfastandslow #AAAI2020debate #neurosymbolic #neurosymboliccomputing
‘The Debate of the Next Decade’
– AI DEBATE 2 EXPLORES AGI AND AI ETHICS
Synced: https://syncedreview.com/2020/12/24/the-debate-of-the-next-decade-ai-debate-2-explores-agi-and-ai-ethics/
#MontrealAI #AIDebate #AIDebate2
– AI DEBATE 2 EXPLORES AGI AND AI ETHICS
Synced: https://syncedreview.com/2020/12/24/the-debate-of-the-next-decade-ai-debate-2-explores-agi-and-ai-ethics/
#MontrealAI #AIDebate #AIDebate2
Synced | AI Technology & Industry Review
‘The Debate of the Next Decade’ – AI Debate 2 Explores AGI and AI Ethics | Synced
The four-hour event included three panel discussions: Architecture and Challenges, Insights from Neuroscience and Psychology, and Towards AI We Can Trust.