IROHMS Future Leaders Academy: Keynote - Prof Ah-Hwee Tan - Virtual

We are delighted to invite you to attend one of the Centre for Artificial Intelligence, Robotics and Human-Machine Systems’ (IROHMS) Keynote presentations as part of IROHMS Future Leaders Academy 2022. This Keynote presentation will be delivered by Professor Ah-Hwee Tan, Professor of Computer Science, Singapore Management University.

Title: Cognitive computing: Theories, models and applications

Abstract: Although recent development in machine learning, in particular deep learning, has significantly advanced the field of Artificial Intelligence (AI), data-driven learning-based AI systems are typically designed to solve specific problems by learning from a vast amount of training data. Human cognition, on the other hand, involves a complex interplay of multiple high-level functions, notably self-awareness, memory, reasoning, learning, and problem solving. In this talk, we shall introduce a new computing paradigm known as Cognitive Computing, which is inspired by human cognitive functions and processes. Specifically, we discuss how a family of self-organizing neural network models, collectively known as fusion Adaptive Resonance Theory (fusion ART), may be used to simulate cognitive computation. By extending Adaptive Resonance Theory (ART) into a multi-channel network architecture, fusion ART unifies several important neural models developed over the past decades, including the original ART model for unsupervised learning, Adaptive Resonance Associative Map (ARAM) for supervised learning, and Fusion Architecture for Learning and Cognition (FALCON) for reinforcement learning. Following the notion of embodied cognition, fusion ART, encompassing a suite of universal neural coding and adaptation principles, can also be used as a building block of a memory model called EM-ART for modelling of spatiotemporal episodic memory. This talk shall present selected case studies illustrating how such ART-based cognitive models may be applied to various memory-based applications, such as activities of daily living (ADL) analysis, topological mapping and navigation as well as COVID-19 contact tracing.

Bio: Dr Ah-Hwee Tan received Ph.D. in Cognitive and Neural Systems from Boston University, Master of Science and Bachelor of Science (First Class Honors) in Computer and Information Science from the National University of Singapore. He is currently Professor of Computer Science and Associate Dean (Research) at the School of Computing and Information Systems (SCIS), Singapore Management University (SMU). Before joining SMU, he was Professor of Computer Science at the School of Computer Science and Engineering (SCSE), Nanyang Technological University, where he last served as the Associate Chair (Research) of the school. Prior to NTU, he was a Senior Member of Research Staff at the A*STAR Institute for Infocomm Research (I2R), spearheading the Text Mining and Intelligent Agents research programmes. His current research interests include cognitive and neural systems, brain-inspired intelligent agents, machine learning, and text mining. Dr. Tan has published over 200 technical papers in major international journals and conferences of his fields, in addition to six edited books and proceedings. He holds two US patents, five Singapore patents, and has spearheaded several A*STAR projects in commercializing a suite of knowledge management and text mining software. He has served as Associate Editor of several journals, including IEEE Transactions on Neural Networks and Learning, IEEE Transactions on SMC Systems, and IEEE Access. He is a Senior Member of IEEE, Member of IEEE Technical Committee on Neural Networks, Vice Chair of IEEE CIS Task Force on Towards Human-Like Intelligence, and General Co-Chair of 2022 IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2022).

Location: This Keynote will be streamed via Zoom. Link will be provided following registration.

IROHMS Future Leaders Academy will explore research challenges in the fields of artificial intelligence, robotics, and human-machine systems, highlighting the transformational research, strong industrial and public sector engagement, and delivery of sustainable, impactful solutions that we are recognised for. Over a period of three weeks, commencing 7 June 2022, guests will be invited to join six keynotes, industry talks, workshops, and tours of our new and improved laboratories: IROHMS Simulation Laboratory, Autonomous Systems and Robotics Laboratory, and Human-Machine Interaction Laboratory.

Prif gyflwyniad 4: Yr Athro Ah-Hwee Tan (Prifysgol Pynciau Rheoli Singapôr)

16eg Mehefin 2022, 15:30-16:30 BST

Mae’n dda gyda ni eich gwahodd i un o brif gyflwyniadau Canolfan Deallusrwydd Artiffisial, Roboteg a Sustemau Peiriannau Dynol yn rhan o Academi Arweinwyr y Dyfodol 2022. Yr Athro Ah-Hwee Tan, Athro Cyfrifiadureg Prifysgol Pynciau Rheoli Singapôr, fydd yn rhoi’r cyflwyniad hwn.

Teitl: Cognitive computing: Theories, models and applications

Crynodeb: Er bod deallusrwydd artiffisial yn mynd o nerth i nerth o ganlyniad i rai datblygiadau diweddar, mae tuedd i lunio sustemau datrys problemau penodol trwy ddysgu darnau helaeth o ddeunydd hyfforddi. Ar y llaw arall, mae pobl yn gweithredu trwy gyfuniad cymhleth o swyddogaethau lefel uchel megis hunanymwybyddiaeth, y cof, rhesymu, dysgu a datrys problemau. Yn y cyflwyniad hwn, byddwn ni’n trafod agwedd newydd o’r enw cyfrifiadura gwybyddol sydd wedi’i seilio ar swyddogaethau a phrosesau gwybyddol pobl. Yn benodol, byddwn ni’n trafod sut y gallwn ni ddefnyddio teulu o fodelau rhwydwaith niwral hunandrefnu (damcaniaeth cyseiniant addasol) i efelychu cyfrifiant gwybyddol. Trwy estyn y ddamcaniaeth honno i bensaernïaeth rhwydwaith aml ei sianeli, gallwn ni uno rhai modelau niwral pwysig sydd wedi’u llunio yn ystod y degawdau diwethaf hyn megis yr un gwreiddiol ar gyfer dysgu heb oruchwylio, map cyswllt cyseiniant addasol ar gyfer dysgu o dan oruchwyliwr a phensaernïaeth cyfuno dysgu a gwybyddiaeth ar gyfer dysgu atgyfnerthu. Yn ôl y syniad o wybyddiaeth ymgorfforedig, mae modd defnyddio damcaniaeth cyfuno ac iddi set o egwyddorion codio ac addasu niwral cyffredinol yn rhan o broses llunio model cof o’r enw EM-ART i fodelu atgofion am leoedd ac amser, hefyd. Bydd yn y cyflwyniad hwn astudiaethau sy’n dangos sut y gallwn ni ddefnyddio modelau gwybyddol o’r fath i amryw ddibenion lle mae angen cof megis dadansoddi gweithgareddau bywyd beunyddiol, mapio a llywio tirweddau ac olrhain pobl fu’n ymwneud â COVID-19.

Bywgraffiad: Enillodd y Dr Ah-Hwee Tan Ph.D. Sustemau Gwybyddol a Niwral ym Mhrifysgol Boston ac MSc a BSc (Anrhydedd Dosbarth Cyntaf) Gwyddorau Cyfrifiadureg a Gwybodaeth ym Mhrifysgol Cenedlaethol Singapôr. Mae yn swyddi Athro Gwyddorau Cyfrifiadureg a Deon Cyswllt Ymchwil Ysgol Sustemau Cyfrifiadureg a Gwybodaeth Prifysgol Pynciau Rheoli Singapôr. Cyn ei rolau presennol, bu yn swyddi Athro Gwyddorau Cyfrifiadureg Ysgol Gwyddorau Cyfrifiadureg a Pheirianneg Prifysgol Dechnolegol Nanyang a Chadeirydd Cyswllt (Ymchwil) yno. Cyn hynny, bu’n uwch aelod o staff ymchwil Sefydliad yr Ymchwil i Wybodaeth a Chyfathrebu (I2R), lle yr arweiniodd rhaglenni ymchwil cloddio testunau ac asiantau deallus. Mae’i ymchwil bresennol yn ymwneud â sustemau gwybyddol a niwral, asiantau deallus sy’n efelychu’r ymennydd, dysgu peiriannol a chloddio testunau. Mae’r Dr Tan wedi cyhoeddi dros 200 o bapurau technegol mewn cyfnodolion rhyngwladol o bwys a chynadleddau am ei feysydd, yn ogystal â chwe llyfr a chofnodion wedi’u golygu. Mae ganddo ddwy hawlfraint yn UDA a phump yn Singapôr, ac mae wedi arwain nifer o brosiectau A*STAR wrth fasnacheiddio cyfres o feddalwedd rheoli gwybodaeth a chloddio testunau. Bu’n olygydd cyswllt i nifer o gyfnodolion megis IEEE Transactions on Neural Networks and Learning, IEEE Transactions on SMC Systems ac IEEE Access. Mae'n uwch aelod o IEEE, yn aelod o Bwyllgor Technegol IEEE dros Rwydweithiau Niwral, yn Is-Gadeirydd i Dasglu IEEE CIS (Tuag at Ddeallusrwydd Pobl) ac yn brif gyd-gadeirydd i Gyfres Sumposiwm IEEE 2022 ar Wybodaeth Gyfrifiadurol (IEEE SSCI 2022).