Auteur : Dagenais, Mylène

Usef FAGHIHI – 16 novembre 2023

Titre : Algorithmes de Deep Learning flous causaux

Résumé :

Je donnerai un bref aperçu de l'inférence causale et de la manière dont les règles de la logique floue peuvent améliorer le raisonnement causal (Faghihi, Robert, Poirier & Barkaoui, 2020). Ensuite, j'expliquerai comment nous avons intégré des règles de logique floue avec des algorithmes d'apprentissage profond, tels que l'architecture de transformateur Big Bird (Zaheer et al., 2020). Je montrerai comment notre modèle de causalité d'apprentissage profond flou a surpassé ChatGPT sur différentes bases de données dans des tâches de raisonnement (Kalantarpour, Faghihi, Khelifi & Roucaut, 2023). Je présenterai également quelques applications de notre modèle dans des domaines tels que la santé et l'industrie. Enfin, si le temps le permet, je présenterai deux éléments essentiels de notre modèle de raisonnement causal que nous avons récemment développés : l'Effet Causal Variationnel Facile Probabiliste (PEACE) et l'Effet Causal Variationnel Probabiliste (PACE) (Faghihi & Saki, 2023).

Bio :

Usef FAGHIHI est professeur adjoint à l'Université du Québec à Trois-Rivières. Auparavant, Usef était professeur à l'Université d'Indianapolis aux États-Unis. Usef a obtenu son doctorat en Informatique Cognitive à l'UQAM. Il est ensuite allé à Memphis, aux États-Unis, pour effectuer un post-doctorat avec le professeur Stan Franklin, l'un des pionniers de l'intelligence artificielle. Ses centres d'intérêt en recherche sont les architectures cognitives et leur intégration avec les algorithmes d'apprentissage profond.

Références :

Faghihi, U., Robert, S., Poirier, P., & Barkaoui, Y. (2020). From Association to Reasoning, an Alternative to Pearl’s Causal Reasoning. In Proceedings of AAAI-FLAIRS 2020. North-Miami-Beach (Florida).

Faghihi, U., & Saki, A. (2023). Probabilistic Variational Causal Effect as A new Theory for Causal Reasoning. arXiv preprint arXiv:2208.06269.

Kalantarpour, C., Faghihi, U., Khelifi, E., & Roucaut, F.-X. (2023). Clinical Grade Prediction of Therapeutic Dosage for Electroconvulsive Therapy (ECT) Based on Patient’s Pre-Ictal EEG Using Fuzzy Causal Transformers. Paper presented at the International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2023, Tenerife, Canary Islands, Spain.

Zaheer, M., Guruganesh, G., Dubey, K. A., Ainslie, J., Alberti, C., Ontanon, S., . . . Yang, L. (2020). Big bird: Transformers for longer sequences. Advances in neural information processing systems, 33, 17283-17297.

Casey KENNINGTON – 9 novembre 2023

Titre : Robotic Grounding and LLMs: Advancements and Challenges

Résumé :

Large Language Models (LLMs) are primarily trained using large amounts of text, but there have also been noteworthy advancements in incorporating vision and other sensory information into LLMs. Does that mean LLMs are ready for embodied agents such as robots? While there have been important advancements, technical and theoretical challenges remain including use of closed language models like ChatGPT, model size requirements, data size requirements, speed requirements, representing the physical world, and updating the model with information about the world in real time. In this talk, I explain recent advance on incorporating LLMs into robot platforms, challenges, and opportunities for future work. 

Bio :

Casey KENNINGTON is associate professor in the Department of Computer Science at Boise State University where he does research on spoken dialogue systems on embodied platforms. His long-term research goal is to understand what it means for humans to understand, represent, and produce language. His National Science Foundation CAREER award focuses on enriching small language models with multimodal information such as vision and emotion for interactive learning on robotic platforms. Kennington obtained his PhD in Linguistics from Bielefeld University, Germany. 

References

Josue Torres-Foncesca, Catherine Henry, Casey Kennington. Symbol and Communicative Grounding through Object Permanence with a Mobile Robot. In Proceedings of SigDial, 2022. 

Clayton Fields and Casey Kennington. Vision Language Transformers: A Survey. arXiv, 2023.

Casey Kennington. Enriching Language Models with Visually-grounded Word Vectors and the Lancaster Sensorimotor Norms. In Proceedings of CoNLL, 2021 Casey Kennington. On the Computational Modeling of Meaning: Embodied Cognition Intertwined with Emotion. arXiv, 2023. 

Eric SCHULZ – 2 novembre 2023

Titre : Machine Psychology

Résumé :

Large language models are on the cusp of transforming society while they permeate into many applications. Understanding how they work is, therefore, of great value. We propose to use insights and tools from psychology to study and better understand these models. Psychology can add to our understanding of LLMs and provide a new toolkit for explaining LLMs by providing theoretical concepts, experimental designs, and computational analysis approaches. This can lead to a machine psychology for foundation models that focuses on computational insights and precise experimental comparisons instead of performance measures alone. I will showcase the utility of this approach by showing how current LLMs behave across a variety of cognitive tasks, as well as how one can make them more human-like by fine-tuning on psychological data directly.

Bio :

Eric SCHULZ, Max-Planck Research Group Leader, Tuebingen University works on the building blocks of intelligence using a mixture of computational, cognitive, and neuroscientific methods. He has worked with Maarten Speekenbrink on generalization as function learning and Sam Gershman and Josh Tenenbaum.

Références

Binz, M., & Schulz, E. (2023). Using cognitive psychology to understand GPT-3. Proceedings of the National Academy of Sciences, 120(6), e2218523120

Akata, E., Schulz, L., Coda-Forno, J., Oh, S. J., Bethge, M., & Schulz, E. (2023). Playing repeated games with Large Language Models. arXiv preprint arXiv:2305.16867.

Allen, K. R., Brändle, F., Botvinick, M., Fan, J., Gershman, S. J., Griffiths, T. L., ... & Schulz, E. (2023). Using Games to Understand the Mind

Binz, M., & Schulz, E. (2023). Turning large language models into cognitive models. arXiv preprint.

Dor ABRAHAMSON – 26 octobre 2023

Titre : Enactivist Symbol Grounding: From Attentional Anchors to Mathematical Discourse

Résumé :

According to the embodiment hypothesis knowledge is the capacity for perceptuomotor enactment, situated in the world as much as in the body: a way of engaging the environment in anticipation of accomplishing interactions. What does this mean for educational practice? What is the embodiment or enactment of abstract ideas, like justice, photosynthesis, or algebra? What is the teacher’s role in embodied designs for learning? I will describe my lab’s educational design-based collaborative research on mathematical learning, and how we came to view in the analysis and promotion of content learning. I will describe how students spontaneously generate perceptual solutions to motor-control problems. These then become verbal through adopting symbolic artifacts provided by the teacher. This approach can also help students with diverse sensorimotor capacities.

Bio :

Dor ABRAHAMSON is Professor in the Graduate School of Education at the University of California Berkeley, where he established the Embodied Design Research Laboratory devoted to pedagogical technologies for teaching and learning mathematics. He is particularly interested in relations between learning to move in new ways and learning mathematicaal concepts. His research draws on embodied cognition, dynamic systems theory, and sociocultural theory.

References

Abrahamson, D., & Sánchez-García, R. (2016). Learning is moving in new ways: The ecological dynamics of mathematics education. Journal of the Learning Sciences, 25(2), 203-239. https://doi.org/10.1080/10508406.2016.1143370

Abrahamson, D. (2021). Grasp actually: An evolutionist argument for enactivist mathematics education. Human Development, 65(2), 1–17. https://doi.org/10.1159/000515680

Shvarts, A., & Abrahamson, D. (2023). Coordination dynamics of semiotic mediation: A functional dynamic systems perspective on mathematics teaching/learning. In T. Veloz, R. Videla, & A. Riegler (Eds.), Education in the 21st century [Special issue]. Constructivist Foundations, 18(2), 220–234. https://constructivist.info/18/2 

Melanie MITCHELL – 19 octobre 2023

Titre : The Debate Over “Understanding” in AI’s Large Language Models

Résumé :

I will survey a current, heated debate in the AI research community on whether large pre-trained language models can be said -- in any important sense -- to "understand" language and the physical and social situations language encodes. I will describe arguments that have been made for and against such understanding, and, more generally, will discuss what methods can be used to fairly evaluate understanding and intelligence in AI systems.  I will conclude with key questions for the broader sciences of intelligence that have arisen in light of these discussions. 

Biographie :

Melanie Mitchell is Professor at the Santa Fe Institute. Her current research focuses on conceptual abstraction and analogy-making in artificial intelligence systems.  Melanie is the author or editor of six books and numerous scholarly papers in the fields of artificial intelligence, cognitive science, and complex systems. Her 2009 book Complexity: A Guided Tour (Oxford University Press) won the 2010 Phi Beta Kappa Science Book Award, and her 2019 book Artificial Intelligence: A Guide for Thinking Humans (Farrar, Straus, and Giroux) is a finalist for the 2023 Cosmos Prize for Scientific Writing. 

Références:

Mitchell, M. (2023). How do we know how smart AI systems are? Science, 381(6654), adj5957.

Mitchell, M., & Krakauer, D. C. (2023). The debate over understanding in AI’s large language models. Proceedings of the National Academy of Sciences, 120(13), e2215907120.

Millhouse, T., Moses, M., & Mitchell, M. (2022). Embodied, Situated, and Grounded Intelligence: Implications for AI. arXiv preprint arXiv:2210.13589.

Titre : Rethinking the Physical Symbol Systems Hypothesis

Résumé :

It is now more than a half-century since the Physical Symbol Systems Hypothesis (PSSH) was first articulated as an empirical hypothesis.  More recent evidence from work with neural networks and cognitive architectures has weakened it, but it has not yet been replaced in any satisfactory manner.  Based on a rethinking of the nature of computational symbols – as atoms or placeholders – and thus also of the systems in which they participate, a hybrid approach is introduced that responds to these challenges while also helping to bridge the gap between symbolic and neural approaches, resulting in two new hypotheses, one – the Hybrid Symbol Systems Hypothesis (HSSH) – that is to replace the PSSH and the other focused more directly on cognitive architectures.  This overall approach has been inspired by how hybrid symbol systems are central in the Common Model of Cognition and the Sigma cognitive architectures, both of which will be introduced – along with the general notion of a cognitive architecture – via “flashbacks” during the presentation.

Biographie :

Paul S. ROSENBLOOM is a Professor Emeritus of Computer Science in the Viterbi School of Engineering at the University of Southern California (USC).  His research has focused on cognitive architectures (models of the fixed structures and processes that together yield a mind), such as Soar and Sigma; the Common Model of Cognition (a partial consensus about the structure of a human-like mind); dichotomic maps (structuring the space of technologies underlying AI and cognitive science); “essential” definitions of key concepts in AI and cognitive science (such as intelligence, theories, symbols, and architectures); and the relational model of computing as a great scientific domain (akin to the physical, life and social sciences).

References

Rosenbloom, P. S. (2023). Rethinking the Physical Symbol Systems Hypothesis.  In Proceedings of the 16^th International Conference on Artificial General Intelligence (pp. 207-216).  Cham, Switzerland: Springer.  

Laird, J. E., Lebiere, C. & Rosenbloom, P. S. (2017). A Standard Model of the Mind: Toward a Common Computational Framework across Artificial Intelligence, Cognitive Science, Neuroscience, and Robotics. AI Magazine, 38, 13-26.  

Rosenbloom, P. S., Demski, A. & Ustun, V. (2016).  The Sigma cognitive architecture and system: Towards functionally elegant grand unification. Journal of Artificial General Intelligence, 7, 1-103.  

Rosenbloom, P. S., Demski, A. & Ustun, V. (2016). Rethinking Sigma’s graphical architecture: An extension to neural networks.  Proceedings of the 9^th Conference on Artificial General Intelligence (pp. 84-94).  

Titre : Understanding Linguistic and Reasoning Mechanisms in Large Language Models

Résumé :

Large language models (LLMs) appear to exhibit human-level abilities on a range of tasks, yet they are notoriously considered to be "black boxes", and little is known about the internal representations and mechanisms that underlie their behavior. This talk will discuss recent work which seeks to illuminate the processing that takes place under the hood. I will focus in particular on questions related to LLM's ability to represent abstract, compositional, and content-independent operations of the type assumed to be necessary for advanced cognitive functioning in humans.

Biographie :

Ellie PAVLICK is an Assistant Professor of Computer Science at Brown University. She received her PhD from University of Pennsylvania in 2017, where her focus was on paraphrasing and lexical semantics. Ellie’s research is on cognitively-inspired approaches to language acquisition, focusing on grounded language learning and on the emergence of structure (or lack thereof) in neural language models. Ellie leads the language understanding and representation (LUNAR) lab, which collaborates with Brown’s Robotics and Visual Computing labs and with the Department of Cognitive, Linguistic, and Psychological Sciences.

RÉFÉRENCES:

Tenney, Ian, Dipanjan Das, and Ellie Pavlick. "BERT Rediscovers the Classical NLP Pipeline." Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019. https://arxiv.org/pdf/1905.05950.pdf

Pavlick, Ellie. "Symbols and grounding in large language models." Philosophical Transactions of the Royal Society A 381.2251 (2023): 20220041. https://royalsocietypublishing.org/doi/pdf/10.1098/rsta.2022.0041

Lepori, Michael A., Thomas Serre, and Ellie Pavlick. "Break it down: evidence for structural compositionality in neural networks." arXiv preprint arXiv:2301.10884 (2023). https://arxiv.org/pdf/2301.10884.pdf

Merullo, Jack, Carsten Eickhoff, and Ellie Pavlick. "Language Models Implement Simple Word2Vec-style Vector Arithmetic." arXiv preprint arXiv:2305.16130 (2023). https://arxiv.org/pdf/2305.16130.pdf

Dave CHALMERS – 28 septembre 2023

Titre : From the History of Philosophy to AI: Does Thinking Require Sensing?

Résumé :

There has recently been widespread discussion of whether large language models might be sentient or conscious. Should we take this idea seriously? I will discuss the underlying issue and will break down the strongest reasons for and against. I suggest that given mainstream assumptions in the science of consciousness, there are significant obstacles to consciousness in current models: for example, their lack of recurrent processing, a global workspace, and unified agency. At the same time, it is quite possible that these obstacles will be overcome in the next decade or so. I conclude that while it is somewhat unlikely that current large language models are conscious, we should take seriously the possibility that extensions and successors to large language models may be conscious in the not-too-distant future.

Biographie :

David Chalmers is University Professor of Philosophy and Neural Science and co-director of the Center for Mind, Brain, and Consciousness at New York University. He is the author of The Conscious Mind (1996), Constructing The World (2010), and Reality+: Virtual Worlds and the Problems of Philosophy (2022). He is known for formulating the “hard problem” of consciousness, and (with Andy Clark) for the idea of the “extended mind,” according to which the tools we use can become parts of our minds.

Références

Chalmers, D. J. (2023). Could a large language model be conscious?. arXiv preprint arXiv:2303.07103.

Chalmers, D.J. (2022) Reality+: Virtual worlds and the problems of philosophy. Penguin

Chalmers, D. J. (1995). Facing up to the problem of consciousness. Journal of Consciousness Studies, 2(3), 200-219.

Clark, A., & Chalmers, D. (1998). The extended mind. Analysis, 58(1), 7-19.

Dimitri COELHO MOLLO – 21 septembre 2023

Titre : Grounding in Large Language Models: lessons for building functional ontologies for AI

Résumé :

My aim in this talk is twofold. First, I will rehearse the arguments, in joint work with Raphaël Millière, that motivate the claim that language grounding (but not language understanding) is possible, and in some cases actual, at least in some current Large Language Models (LLMs). That does not mean, however, that the way language grounding works in LLMs is similar, let alone identical, to how grounding works in humans.  Such differences open up two options: narrowing down the notion of grounding to capture only the phenomenon in humans; or pluralism about grounding, allowing the notion to extend more broadly to systems that fulfil the appropriate requirements for possessing intrinsic content. In the second part of the talk, taking LLMs as a case study, I will argue that pluralism is the most promising road, one that invites the application to AI of recent work in comparative and cognitive psychology, and especially the ongoing project of looking for appropriate ontologies to account for cognition and intelligence. Given the doubtful cognitive status of current AI systems, I will suggest that looking for explanatorily powerful functional ontologies can help us to better understand the capabilities and limitations of current AI systems, as well as potential ways forward for the field.

Biographie :

I am an Assistant Professor with focus in Philosophy of Artificial Intelligence at the Department of Historical, Philosophical and Religious Studies,  at Umeå University, Sweden, and focus area coordinator at TAIGA (Centre for Transdisciplinary AI), for the area 'Understanding and Explaining Artificial Intelligence'. I am also an external Principal Investigator at the Science of Intelligence Cluster, in Berlin, Germany. My research focuses on foundational and epistemic questions within artificial intelligence and cognitive science, looking for ways to improve our understanding of mind, cognition, and intelligence in biological and artificial systems. My work often intersects issues in Ethics of Artificial Intelligence, Philosophy of Computing, and Philosophy of Biology.

Références:

Coelho Mollo and Millière (2023), The Vector Grounding Problem - https://arxiv.org/abs/2304.01481

Francken, Slors, Craver (2022), Cognitive ontology and the search for neural mechanisms: three foundational problems - https://link.springer.com/article/10.1007/s11229-022-03701-2

Benjamin BERGEN – 14 septembre 2023

Titre : LLMs are impressive but we still need grounding to explain human cognition

RÉSUMÉ :

Human cognitive capacities are often explained as resulting from grounded, embodied, or situated learning. But Large Language Models, which only learn on the basis of word co-occurrence statistics, now rival human performance in a variety of tasks that would seem to require these very capacities. This raises the question: is grounding still necessary to explain human cognition? I report on studies addressing three aspects of human cognition: Theory of Mind, Affordances, and Situation Models. In each case, we run both human and LLM participants on the same task and ask how much of the variance in human behavior is explained by the LLMs. As it turns out, in all cases, human behavior is not fully explained by the LLMs. This entails that, at least for now, we need grounding (or, more accurately, something that goes beyond statistical language learning) to explain these aspects of human cognition. I’ll conclude by asking but not answering a number of questions, like, How long will this remain the case? What are the right criteria for an LLM that serves as a proxy for human statistical language learning? and, How could one tell conclusively whether LLMs have human-like intelligence?

BIOGRAPHIE :

Ben BERGEN is Professor of Cognitive Science at UC San Diego, where he directs the Language and Cognition Lab. His research focuses on language processing and production with a special interest in meaning. He’s also the author of 'Louder than Words: The New Science of How the Mind Makes Meaning' and 'What the F: What Swearing Reveals about Our Language, Our Brains, and Ourselves.’

RÉFÉRENCES:

Trott, S., Jones, C., Chang, T., Michaelov, J., & Bergen, B. (2023). Do Large Language Models know what humans know? Cognitive Science 47(7): e13309.

Chang, T. & B. Bergen (2023). Language Model Behavior: A Comprehensive Survey. Computational Linguistics.

Michaelov, J., S. Coulson, & B. Bergen (2023). Can Peanuts Fall in Love with Distributional Semantics? Proceedings of the 45th Annual Meeting of the Cognitive Science Society. Austin, TX: Cognitive Science Society.

Jones, C., Chang, T., Coulson, S., Michaelov, J., Trott, T., & Bergen, B. (2022). Distributional Semantics Still Can't Account for Affordances. Proceedings of the 44th Annual Conference of the Cognitive Science Society. Austin, TX: Cognitive Science Society.