Log in

Login to your account

Username *
Password *
Remember Me
From Brain Science to Intelligent Machines

Multi-modal aggregation explains why a picture is worth a thousand words

Date: Tuesday 2/2/2016

Venue: MS105 (Boardroom)

Time: 2.45 pm

Speaker: Prof. Khurshid Ahmad

Affiliation:  School of Computer Science and Statistics, Trinity College, The University of Dublin

                 Project Co-ordinator, EU FP7 Slandail Project** (2014-2017)

 

Multi-modal aggregation explains why a picture is worth a thousand words

By 
Prof. Khurshid Ahmad

School of Computer Science and Statistics, Trinity College, The University of Dublin

Abstract

The central issue about the utility of images, video and still, in decision making is the retrieval of images from an arbitrary collection of images in a timely manner with as great a precision as is possible.  This question is as relevant to photo (and now) an image album as it is to the operation of disaster managers.  The research question related to the issue is this: Can we make a corpus of images, as accessible to retrieval, browsing and summarization as a text corpus is now? This is a revolutionary notion that would change all multi-modal environments such as the World Wide Web.

The barrier to this notion is that, whereas the codes designed for the expression and retrieval of information in texts are well understood in computational terms, analogous codes for images, if present at all, are not. From what we know currently about human and animal behaviour is the usage of one modality (say language or sound, spatial perception) in understanding information received in another modality (say vision) – the collateral use of texts, sounds, spatial perception in understanding the visual signals appears vary valuable.  Visual enumeration or subitization, aspects of synaesthesia, appreciation of (abstract) art, and observations of humans involved in critical decision making, for example, show this multi-modality at work. The codes that have to be designed for expression and retrieval of information in images may be abstracted using data which is collateral to an image.  

I will describe how we can begin to automatically index images and videos using image features, shape, colour, and texture distribution plus features of a text that is collateral to an image.  The collateral information has many sources – for example, manual annotation, linguistic description of an image found embedded in a text, sound track associated with a video.  The image and text vectors can be used for training a system for associating image features that a set of singe and compound words that have a high probability of association with image features of images.  Such a system, in principle, can not only perform picture naming but also can do word illustration.  A neural network based architecture will be presented which has been implemented with a modicum of success in automatically naming pictures and in illustrating words.

Spiking neural networks, spatio temporal data, personalised modelling and applications in bio and neuroinformatics

Date: Wednesday 28/10/2015

Venue: MS020

Time: 11.00 am

Speaker: Prof. Nikola Kasabov

Affiliation:  Auckland University of Technology, New Zealand

Spiking neural networks, spatio temporal data, personalised modelling and applications in bio and neuroinformatics

By
Prof. Nikola Kasabov

Auckland University of Technology, New Zealand

Abstract

The talk presents a new spiking neural network architecture called NeuCube, its main principles and a design procedure for applications on temporal and spatio temporal data with examples in bio and neuroinformatics.

Note:
Presentation slides can be downloaded from the following link:     https://goo.gl/1I5wT5  

Short Bio

More information about Prof. Nikola Kasabov can be found at:   http://www.kedri.aut.ac.nz/staff/staff-profiles/professor-nikola-kasabov

Wednesday 28/10/2015

Majority Spanning Trees, Co-trees and their Applications

Date: Friday 25/9/2015

Venue: MS105 (Boardroom)

Time: 11.00 am

Speaker: Dr. Mohammad Kaykobad

Affiliation: Bangladesh University of Engineering and Technology

 

Majority Spanning Trees, Co-trees and their Applications

By
Dr. Mohammad Kaykobad

Bangladesh University of Engineering and Technology

Abstract

A new class of spanning trees, called Majority Spanning trees, and Majority Co-trees have been defined and their existence in digraphs, with non-negative weights on edges, have been established. The applications of Majority Spanning Trees to Minimum Connection Time Problem, Optimal Ranking of a Round Robin Tournament and settling debts have been shown.

 

Short Bio

Mohammad Kaykobad is a computer scientist, educator, author and columnist from Bangladesh University of Engineering and Technology. Along with Muhammed Zafar Iqbal, he started the national mathematics Olympiad. Prof. Kaykobad is also a pioneer in introducing Science Olympiad organized by Bangladesh Academy of Sciences and Informatics Olympiad in Bangladesh. He wrote a number of books on recreational mathematics. Currently he is a professor of Computer Science in Bangladesh University of Engineering and Technology. He was a visiting professor at Kyung Hee University, Korea Advanced Institute of Science and Technology, South Korea and the Chinese University of Hong Kong. He has been involved in ACM International Collegiate Programming Contest for the last 17 years and received outstanding coach award (2002, Hawaii) and Senior Coach award (2013, St Petersburg). He also received Bangladesh Academy of Sciences Gold Medal for Physical Sciences Senior Group, Gold medal for his contribution to CS Education and Programming Culture in the country. He obtained his PhD from the Flinders University of South Australia in 1986. He is a Fellow of Bangladesh Academy of Sciences. Some of his professional activities can be found at Wikipedia: http://en.wikipedia.org/wiki/Mohammad_Kaykobad.

 

Mohammad Kaykobad is a computer scientist, educator, author and columnist from Bangladesh University of Engineering and Technology. Along with Muhammed Zafar Iqbal, he started the national mathematics Olympiad. Prof. Kaykobad is also a pioneer in introducing Science Olympiad organized by Bangladesh Academy of Sciences and Informatics Olympiad in Bangladesh. He wrote a number of books on recreational mathematics.


Currently he is a professor of Computer Science in Bangladesh University of Engineering and Technology. He was a visiting professor at Kyung Hee University, Korea Advanced Institute of Science and Technology, South Korea and the Chinese University of Hong Kong. He has been involved in ACM International Collegiate Programming Contest for the last 17 years and received outstanding coach award (2002, Hawaii) and Senior Coach award (2013, St Petersburg). He also received Bangladesh Academy of Sciences Gold Medal for Physical Sciences Senior Group, Gold medal for his contribution to CS Education and Programming Culture in the country.


He obtained his PhD from the Flinders University of South Australia in 1986. He is a Fellow of Bangladesh Academy of Sciences. Some of his professional activities can be found at Wikipedia:
http://en.wikipedia.org/wiki/Mohammad_Kaykobad.

On the origins of agency

Date: Tuesday 29/9/2015

Venue: MS105 (Boardroom)

Time: 12.00 noon

Speaker: Prof. Scott Kelso

Affiliation: Florida Atlantic University

On the origins of agency

By
Prof. Scott Kelso

Florida Atlantic University

Abstract

The word “agent” is commonplace in computer science and artificial intelligence, as well as many other fields. But what principles and mechanisms underlie the emergence of agency? The question of agency and directedness in living systems has puzzled philosophers and scientists for centuries. I will present an analysis and theoretical model of experiments on human infants and suggest an answer that is based on the principles and mechanisms of coordination dynamics. The birth of agency and its causative powers ("I do", "I can do") is shown to correspond to a phase transition in a coupled dynamical system whose key variables span the interaction between the organism and its environment. The main mechanism underlying the origin of agency is autocatalytic and involves positive feedback: when the baby’s initially spontaneous movements cause the world to change, their perceived consequences have a sudden and sustained amplifying effect on the baby’s further actions. Some implications of this theory will be discussed.

Short Bio

Using a combination of brain imaging, behavioral methods and computational modeling, Scott Kelso’s research focuses on how the brain is coordinated on multiple levels, all the way from cells to cognition and social behavior (see http://www.ccs.fau.edu/hbbl3/). Kelso holds the Glenwood and Martha Creech Eminent Scholar Chair in Science at Florida Atlantic University in Boca Raton where he is also Professor of Psychology and Neuroscience, Biological Sciences and Biomedical Sciences. From 1985-2005 he served as the Founding Director of Florida Atlantic’s Center for Complex Systems and Brain Sciences where he also led the NIH’s National Training Program in this new interdisciplinary field. Prior to his current position, Kelso was Senior Research Scientist at Yale University’s Haskins Laboratories and Professor of Psychology and Biobehavioral Sciences at the University of Connecticut. Since 2009, Kelso has been Visiting Professor at the Intelligent Systems Research Centre in Ulster University’s Magee Campus in Derry, N. Ireland the place where he was born

Kelso and colleagues’ research has been published in Science and Nature as well as other prominent journals in the fields of neuroscience, physics, biology and psychology. His books include Dynamic Patterns: the Self-Organization of Brain and Behavior (MIT Press, 1995), Coordination Dynamics (Springer, 2004) and The Complementary Nature published by MIT Press in 2006. Kelso is an elected Fellow of APA, APS, SEP and AAAS and has received a number of honors and awards for his work, including the MERIT, Senior Scientist and Director’s Innovations Awards from the U.S. National Institute of Health, the Distinguished Alumni Research Achievement Award from the University of Wisconsin, Madison and the Docteur Honoris Causa degree from the Republic of France and the University of Toulouse (est. 1228). In 2007 he was named Pierre de Fermat Laureate and in 2011 he was the recipient of the Bernstein Prize for his fundamental work on how the brain controls movement. Trained in a specifically interdisciplinary setting, Kelso’s PhD students and Postdoctoral fellows have gone on to careers in some of the top academic and research institutions in the world.

Cable-driven Exoskeletons for Human Movement Training

 

Cable-driven Exoskeletons for Human Movement Training

by

Professor Sunil K. Agrawal

Department of Mechanical Engineering & of Rehabilitation and Regenerative Medicine

Columbia University, New York, NY

(Email: This email address is being protected from spambots. You need JavaScript enabled to view it.)

 

Abstract:

Robotics is emerging as a tool for training of human skills and functional movements. Robotics also provides the tools to probe the human neuromuscular system and to study how the human body would respond to simulated external conditions. While traditional exoskeletons are made out of rigid links, our group at Columbia University Robotics and Rehabilitation (ROAR) Laboratory has designed a series of novel light-weight cable-driven exoskeletons and devices - CAREX for training of the arm movements, C-ALEX for training of the leg movements, TPAD for active control of the pelvis. The talk will describe both the scientific challenges in designing a cable-driven system as well as a series of human experiments conducted with these designs. These experiments were targeted at movement retraining of young healthy adults, falls prevention of elderly, movement retraining of patients with hemiparesis as a result of neurological conditions such as stroke and cerebral palsy.                 

Short Bio:

image002Sunil K. Agrawal received a Ph.D. degree in Mechanical Engineering from Stanford University in 1990. He is currently the Director of Robotics and Rehabilitation (ROAR) Laboratory at Columbia University. He has published close to 400 journal and conference papers. Dr. Agrawal is a Fellow of the ASME and his honors include a NSF Presidential Faculty Fellowship from the White House in 1994, a Bessel Prize from Germany in 2003, a Humboldt US Senior Scientist Award in 2007. He is a recipient of the Best Paper award at the 35th ASME Robotics and Mechanisms Conference in 2011 and a Best Student Paper Award at the IEEE International Conference in Robotics and Automation in 2012. He has held positions as a Distinguished Visiting Professor at Hanyang University in Korea and is currently a Professor of Robotics at the University of Ulster in Northern Ireland. He actively serves on editorial boards of conferences and journals published by the ASME, IEEE, and other professional societies