Le 29 octobre, NeuroQAM présente une conférence en partenariat avec Cerebrum. Conférencier : Robert-Paul Juster, Professeur à la Faculté de médecine - Département de psychiatrie et d’addictologie,
Université de Montréal. Par Zoom. Détails.
Auteur : plourde_mi
Data, Knowledge, and Logic: Modeling and Reasoning for Natural Language Understanding - Séminaire DIC-ISC-CRIA, 7 octobre
Par : Bang Liu
Résumé :
Existing deep learning-based techniques for different NLU tasks are mostly data-intensive and domain-sensitive. However, creating large-amount and high-quality training datasets for NLU tasks, e.g., question answering, are both expensive and time-consuming. In this talk, we will introduce our research on data generation, knowledge expansion, and reasoning over graphs. Specifically, for data augmentation, we generate large-scale and high-quality question-answer pairs from unlabeled text to augment the training data for question answering. For knowledge expansion, we create and expand an ontology with newly discovered concepts or entities to capture the emerging knowledge in the world and keep the ontology dynamically updated. We will also briefly mention our ongoing work about a reinforcement learning-based relational reasoning framework which reasons over relational data and learns the underlying compositional logical rules. Our long-term vision is to design low-resource, knowledge-empowered, and transferable NLU systems and apply them to different domains
Bio :
Bang Liu is an Assistant Professor in the Department of Computer Science and Operations Research (DIRO) at the University of Montreal, and member of Mila – Quebec Institute of Artificial Intelligence. He researches natural language processing and understanding, text mining, and AI applications in different fields. He has produced visible values to both academia and industry. His innovations have been deployed in real-world applications (QQ Browser, Mobile QQ, and WeChat), serving over a billion daily active users. He has published 25+ papers on top conferences and journals, such as SIGMOD, ACL, NAACL, KDD, WWW, ICDM, CIKM, TKDD, and TON.
Jeudi 7 octobre, 10 h 00. Lien zoom : https://uqam.zoom.us/j/85150962901
Connectez-vous 10 à 15 minutes à l’avance, et donnez votre nom complet dès votre entrée pour nous faciliter la tâche de vous admettre au séminaire.
IA et EDI - le cas du TAL pour la préservation et revitalisation des langues autochtones. Séminaire DIC-ISC-CRIA 30 septembre
Par : Ngoc Tan LE
Résumé :
L’IA présente plusieurs défis et enjeux dont l’inclusivité, l’explicabilité, la responsabilité, les biais et la discrimination ainsi que la disponibilité et qualité des données.
Les langues autochtones souffrent du manque de données et de ressources linguistiques, ce qui les rend très menacées de disparition. Ces langues autochtones sont reconnues comme étant des langues polysynthétiques à faibles ressources mais aussi ayant une complexité morphologique et des variations dialectales.
Cette présentation porte sur nos travaux de recherche courants concernant un groupe de langues autochtones, l'inuktitut et l'inuinnaqtun - deux langues inuites. Nous proposons une segmentation morphologique non supervisée basée sur l'approche Adapter Grammars et une étude empirique de la segmentation morphologique à des fins de la traduction automatique neuronale pour langues très peu dotées.
Bio :
Ngoc-Tan Le est actuellement stagiaire post-doctoral à l’UQAM. Il a obtenu un doctorat en informatique cognitive en 2019. Ses intérêts en recherche incluent le traitement automatique des langues naturelles (TALN) et l’intelligence artificielle, notamment pour le développement d’applications et outils d’intelligence artificielle pour les langues et domaines peu dotés ou pauvres en données, dont les langues autochtones et leurs enjeux et réalités.
Jeudi 30 septembre, 10 h 00. Lien zoom https://uqam.zoom.us/j/85150962901. Connectez-vous 10 à 15 minutes à l’avance, et donnez votre nom complet dès votre entrée pour nous faciliter la tâche de vous admettre au séminaire.
Developmental Robotics: From Babies to Robots - Séminaire DIC-ISC-CRIA, 23 septembre
Par : Angelo Cangelosi
Résumé :
The latest developments in AI and machine learning offer an opportunity to advance the design of intelligent robots and human-robot interaction systems, for applications in flexible manufacturing, robot companions for older people and in education. We will introduce the field of Developmental Robotics, part of the wider field of Cognitive Robotics (Cangelosi & Schlesinger 2015; Cangelosi & Asada 2021). This combines AI with robotics by taking inspiration from psychology (e.g. child psychology) and neuroscience. In the talk we briefly present some examples of developmental robotics experiments and videos showing how robots can learn to communicate with people, and can develop social skills such as Theory of Mind to improve the design of trustworthy autonomous systems.
Références :
Cangelosi A, Asada M (Eds.) (2021, in press). Cognitive Robotics. Cambridge, MA: MIT Press.
Cangelosi A, Schlesinger M (2015). Developmental Robotics: From Babies to Robots. Cambridge, MA: MIT Press
Bio :
Angelo Cangelosi currently is Professor of Machine Learning and Robotics at the University of Manchester (UK). He also is Turing Fellow at the Alan Turing Institute London and Visiting Distinguished Fellow at AIST-AIRC Tokyo. His research interests are in developmental robotics, language grounding, human robot-interaction and trust, and robot companions for health and social care. Cangelosi currently is Principal investigator for the ongoing projects “UKRI TAS Trust Node” (EPSRC, 2020-24, £1m), “THRIVE++” (US Air Force Lab, 2018-2023, $1m) and the H2020 projects TRAINCREASE, eLADDA ETN and PERSEO ETN. Overall, Cangelosi has secured over £32m of research grants as coordinator/PI, and produced more than 250 scientific publications. Cangelosi is Editor of the journals Interaction Studies and IET Cognitive Computation and Systems. His book “Developmental Robotics: From Babies to Robots” (MIT Press) was published in January 2015, and recently translated in Chinese and Japanese. His latest book “Cognitive Robotics” (MIT Press), coedited with Minoru Asada, will be published in 2021.
Jeudi 23 septembre, 10 h 00.
Lien zoom https://uqam.zoom.us/j/85150962901. Connectez-vous 10 à 15 minutes à l'avance, et donnez votre nom complet dès votre entrée pour nous faciliter la tâche de vous admettre au séminaire.
9 septembre - Séminaire DIC-ISC-CRIA
Titre : Qu’est-ce que la cognition ?
Par : Étienne Harnad
Date : Jeudi le 9 septembre 2021, 10h00
Résumé :
L’informatique, on sait ce que c’est, mais qu’est-ce que la cognition ? Venez avec vos hypothèses de ce qu’est la cognition. J’apporterai la mienne. Et nous verrons ce que ça donne. On va aussi examiner ce que Turing, le co-inventeur de l’informatique et des sciences cognitives, avait à dire sur le sujet.
Bio :
Étienne Harnad est professeur de psychologie à l’UQAM et directeur de la revue Animal Sentience. Ses domaines de spécialisation sont la perception, le langage et la sentience.
Lien zoom pour y assister (veuillez indiquer votre nom complet dès votre entrée pour nous faciliter la tâche de vous admettre au séminaire) : https://uqam.zoom.us/j/85150962901
16 septembre - Séminaire DIC-ISC-CRIA
Titre : Robot Inner Speech: A Sign of Robot Sentience?
Par : Antonio Chella
Date : Jeudi 16 septembre, 10h00
Résumé :
Inner speech is thoroughly studied in humans and represents an interdisciplinary research issue involving psychology, neuroscience, and pedagogy. Inner speech is generally considered tightly linked to self-consciousness. The seminar will discuss the potential of a robot’s inner speech alone and while cooperating with human partners. A cognitive architecture was designed at the RoboticsLab of the University of Palermo and integrated with standard robot routines into a complex robot framework. Thanks to the robot monologue, the human partner can easily trace the robot’s internal processes. Moreover, the robot can better resolve conflicts leading to successful goal achievement.
The seminar will also present experiments on interactions of the architecture implemented on a Pepper robot by Softbank robotics. Results show that functional and transparency requirements are better met when inner speech accompanies human-robot interaction. Moreover, human-robot interaction sessions were organized to evaluate how inner speech influences human trust in robot sentience, where participants have to set up a table in collaboration with the robot. Participant levels of trust and perception of robot anthropomorphic features increase after experimental interaction with the robot.
References:
https://www.frontiersin.org/articles/10.3389/frobt.2020.00016/full
https://www.cell.com/iscience/pdf/S2589-0042(21)00339-4.pdf
https://www.sciencedirect.com/science/article/pii/S0921889021001238
Bio :
Antonio Chella is a Professor of Robotics at the University of Palermo, Italy and the Director of the Robotics Lab at the Department of Engineering of the same University. He is an Associate Researcher at the Institute for High-Performance Computing and Networking (ICAR) of the Italian National Research Council (CNR), and an Honorary Professor in Machine Learning and Optimisation within the School of Computer Science of the University of Manchester, UK. The primary research expertises of Prof. Chella concern Machine Consciousness, Artificial Intelligence and Cognitive Robotics. He is a fellow of the Italian National Academy of Science, Humanities, and Arts. He received the James S. Albus Medal award of the Biologically Inspired Cognitive Architecture (BICA) Society for the outstanding contribution to the science of BICA and for support and scientific achievement of the BICA Society. He is a founder and Editor in Chief of the Journal of Artificial Intelligence and Consciousness and of the Book Series on Machine Consciousness by World Scientific
Le lien zoom pour y assister est https://uqam.zoom.us/j/85150962901. (veuillez indiquer votre nom complet dès votre entrée pour nous faciliter la tâche de vous admettre au séminaire). S.V.P. vous connecter au moins 10 à 15 minutes en avance.
ContribuLing : a joint contribution of INALCO, Wikimedia, BULAC and UQAM - 3-4 June
The Contribuling project
The ContribuLing project - a joint contribution of INALCO, Wikimedia, BULAC and UQAM - will take place on June 3rd/4th 2021, fully online. Its aim is to offer members of linguistic resource platforms an opportunity to give out presentations on their tools and workshops on their use that will enable would-be users to contribute.
ContribuLing's main goal is to ensure that the largest possible number of contributors can use the platforms. An additional benefit will be to allow the emergence or the development of user groups who share the same tools or platforms. Emphasis will not be laid on producing data sets but on enabling attendees to do so.
Attending the event
Registration is free, but mandatory. More info.
Lauréats de la 1ère bourse de valorisation : projet de mise en valeur des conférences de philosophie à l'ACFAS
Voici les membres de l'équipe de recherche qui s'est mérité la toute première bourse de valorisation de projets de l'ISC, en avril 2021 :
Elisabeth Doyon, doctorante en informatique cognitive, UQAM
Toufik Mechouma, doctorant en informatique cognitive, UQAM
Julien Vallières, étudiant à la maîtrise en langue et littérature françaises, Université McGill
Projet :
Soixante-trois ans de conférences philosophiques (1933-1995) : pilote d’extraction de corpus et d’indexation analytique par forage textuel des Annales de l’ACFAS. Description du projet.
ÉCOLE D'ÉTÉ DE L'ISC : inscriptions toujours possibles
Il reste une journée pour vous inscrire aux 3 derniers jours de l'École d'été, remplis de conférences intéressantes. Alllez voir le programme ! Inscrivez-vous.
31 mars et 1er avril - Séminaires DIC-ISC-CRIA
Mercredi 31 mars 2021 EXCEPTIONNELLEMENT à 19h
Exploring robotic minds using predictive coding and active inference frameworks
Par Jun Tani
Le lien zoom pour y assister est (veuillez indiquer votre nom complet dès votre entrée pour nous faciliter la tâche de vous admettre au séminaire) : https://uqam.zoom.us/j/84473395235
Résumé :
The focus of my research has been to investigate how cognitive agents can acquire structural representation via iterative interaction with the world, exercising agency and learning from resultant perceptual experience. For this purpose, my group has investigated various models analogous to predictive coding and active inference frameworks. For the past two decades, we have applied these frameworks to develop cognitive constructs for robots. My talk attempts to clarify underlying cognitive and mind mechanisms for compositionality, social cognition, and consciousness from analysis of emergent phenomena observed in these robotics experiments.
References:
(1) Tani, J. (2016). “Exploring Robotic Minds: Actions, Symbols, and Consciousness as Self-Organizing Dynamic Phenomena.”, Oxford University Press. link
(2) Tani, J., & White, J. (2020). Cognitive neurorobotics and self in the shared world, a focused review of ongoing research. Adaptive Behavior, 1059712320962158.
Bio:
Jun Tani received the D.Eng. degree from Sophia University, Tokyo in 1995. He started his research career with Sony Computer Science Lab. in 1993. He became a Team Leader of the Laboratory for Behavior and Dynamic Cognition, RIKEN Brain Science Institute, Saitama, Japan in 2001. He became a Full Professor with the Electrical Engineering Department, Korea Advanced Institute of Science and Technology, Daejeon, South Korea in 2012. He is currently a Full Professor with the Okinawa Institute of Science and Technology, Okinawa, Japan. His current research interests include cognitive neuroscience, developmental psychology, phenomenology, complex adaptive systems, and robotics.
Jeudi 1er avril 2021 à 10h30
The challenge of modeling the acquisition of mathematical concepts.
Par Alberto Testolin
Le lien zoom pour y assister est (veuillez indiquer votre nom complet dès votre entrée pour nous faciliter la tâche de vous admettre au séminaire) : https://uqam.zoom.us/j/84473395235
Résumé :
Mathematics is one of the most impressive achievements of human cultural evolution. Despite we perceive it as being overly abstract, it is widely believed that mathematical skills are rooted into a phylogenetically ancient “number sense”, which allows us to approximately represent quantities. However, the relationship between number sense and the subsequent acquisition of symbolic mathematical concepts remains controversial. In this seminar I will discuss how recent advances in AI and deep learning research might allow to investigate how the acquisition of numerical concepts could be grounded into sensorimotor experiences. Success in this challenging enterprise would have immediate implications for cognitive science, but also far-reaching impact for educational practice and for the creation of the next generation of intelligent machines.
References:
1) Zorzi, M., & Testolin, A. (2018). An emergentist perspective on the origin of number sense. Philosophical Transactions of the Royal Society B: Biological Sciences, 373(1740), 20170043.
https://royalsocietypublishing.org/doi/full/10.1098/rstb.2017.0043
2) Overmann, K. A. (2018). Constructing a concept of number. Journal of Numerical Cognition. 4, 464–493.
https://jnc.psychopen.eu/article/view/161/html
Bio:
Dr. Alberto Testolin received the M.Sc. degree in Computer Science and the Ph.D. degree in Psychological Sciences from the University of Padova, Italy, in 2011 and 2015, respectively. In 2019 he was Visiting Scholar at the Department of Psychology at Stanford University. He is currently Assistant Professor at the University of Padova, with a joint appointment at the Department of Information Engineering and the Department of General Psychology. He is broadly interested in artificial intelligence, machine learning and cognitive neuroscience. His main research interests are statistical learning theory, predictive coding, sensory perception, cognitive modeling and applications of deep learning to signal processing and optimization. He is an active member of the IEEE Task Force on Deep Learning.






