The Computer Science Department at the University of Auckland, in association with IT Professionals New Zealand, is pleased to announce the Gibbons Lecture Series for 2017. This year the lectures address aspects of the Steps Towards the Singularity: Artificial Intelligence and its Impact. Machines that mimic cognitive functions which humans associate with other human minds, such as learning and problem solving, are said to be exhibiting Artificial Intelligence or AI. In this series of lectures we will explore what is happening locally. Setting the scene, our lead speaker for 2017, Professor Nikola Kasabov, from Auckland University of Technology, will discuss the progress of AI from its deepest roots to current research frontiers. Of personal interest to many of us, Professor Hans Guesgen, from Massey University, will be talking about the use of AI to improve the lot of elderly citizens. Associate Professor Marcus Frean, from Victoria University of Wellington, will take a more-critical look at the current hot topic of deep learning. Ending the lecture series, with a discussion of the questionable impacts of AI, will be Associate Professor Ian Watson from the University of Auckland.

Lecture 1: AI: From Aristotle to Deep Learning Machines

Speaker: Prof. Nikola Kasabov, Auckland University of Technology

Date & Time: 4 May 2017: 6:00 pm - 7:30 pm

Venue: University of Auckland, Owen G Glenn Building, Room OGGB 3/260-092, Level 0, 12 Grafton Road, Auckland. (There is public parking in the basement of the Owen G Glenn Building at 12 Grafton Road)

Registration: Attendance is free. Please see details for registration


Abstract: The talk presents briefly the main principles used in AI, from Aristotle's true/false, logic, through fuzzy logic, evolutionary computation and neural networks, to arrive at the current state-of-art in AI - the deep learning machines. One particular implementation, dubbed NeuCube, developed in the presenter's KEDRI institute, is designed for deep learning of complex data patterns, both in space and time, and to predict future events.  It uses the latest AI techniques called spiking neural networks (SNN) that mimic the learning capabilities of the human brain. This NZ invention has already been demonstrated on various spatio-temporal data and problems, including: brain EEG and fMRI data; brain-computer interfaces; seismic data for earthquake prediction; environmental data for individual stroke prediction; and others. This is the beginning of understanding complex patterns of changes of variables in Space and Time and their relevance to future events. This is one of science’s biggest challenges and has an enormous impact on our understanding of the dynamics of the micro and the macro worlds; from molecular and brain functioning, to geophysical phenomena, and the universe. More information, along with software and data, can be found in: http://www.kedri.aut.ac.nz.

About the Speaker

Nikola Kasabov received his PhD (Mathematical Sciences) in 1975 from the Technical University of Sofia. He moved to the University of Essex in the UK and, in 1992, to New Zealand as a senior lecturer in the Department of Information Sciences at the University of Otago, quickly advancing to a Professorship by 1999. He moved to AUT in 2002 where he is now the Director of the Knowledge Engineering & Discovery Research Institute and holds a Professorship in Knowledge Engineering in the School of Engineering, Computer and Mathematical Sciences. He has published over 600 works, including 180 journal papers, 12 text books, 28 patents. He has received numerous awards for the quality of his copious research output. He is a Fellow of the IEEE, the IITP and the RSNZ. Professor Kasabov has research interests in Neurocomputation, Artificial Intelligence (Neural Networks, Fuzzy Systems, Evolutionary Computation), Machine Learning, Data Mining and Knowledge Engineering, Neuroinformatics, Bioinformatics.  Much of his current research in the KEDRI institute is based around his NeuCube neurocomputing technology which is being applied to learning and pattern recognition of spatio-temporal data. More information can be found at: http://www.kedri.aut.ac.nz.