27th AIAI Irish Conference on Artificial Intelligence and Cognitive Science

AI and Cognitive Science Applications for Sustainability

December 5-6th 2019
NUI Galway

Programme

The conference will take place at the Institute for Lifecourse and Society (ILAS) on the NUI Galway Campus. A draft outline program is presented here to facilitate travel planning by attendees.

Schedule - Thursday 5th December (Full Day)

08:45 - 09:45 Registration and Coffee
09:45 - 10:20 Welcome (Chair: Edward Curry)
Opening Remarks by President of NUI Galway Professor Ciarán Ó hÓgartaigh
10:20 - 11:40 Session 1 - Numerical Reasoning and Algorithms (Chair: Mathieu d’Aquin)
  • Kalman Filter-based Heuristic Ensemble (KFHE): A new perspective on multi-class ensemble classification using Kalman filters.
  • Arjun Pakrashi and Brian Mac Namee
  • PROFET: Construction and Inference of DBNs Based on Mathematical Models.
  • Hamda Ajmal, Michael Madden and Catherine Enright
  • On the validity of bayesian neural networks for uncertainty estimation.
  • John Mitros and Brian Mac Namee
  • When and Why Metaheuristics Researchers Can Ignore "No Free Lunch" Theorems.
  • James McDermott
11:40 - 12:00 Coffee Break (and Poster Setup)
12:00 - 13:00 Session 2 - Big Data and Machine Learning Applications (Chair: Conor Hayes)
  • Dealing with Stochasticity in Biological ODE Models.
  • Hamda Ajmal, Michael Madden and Catherine Enright
  • Unsupervised Learning Approach for Identifying Sub-genres in Music Scores.
  • Girija Shingte and Mathieu D'Aquin
  • Conversational AI: Social and Ethical Considerations.
  • Elayne Ruane, Abeba Birhane and Anthony Ventresque
13:00 - 14:00 Lunch Break and Poster Session (Chair: Annalina Caputo)
14:00 - 15:20 Session 3 - Deep Learning (Chair: Niki Pavlopoulou)
  • Deep Learning Human Activity Recognition.
  • David Browne, Steven Prestwich and Michael Gierin
  • Deconvolutional Pixel Layer Model for Road segmentation without Human Assistance.
  • Abdul Wahid and Muhammad Intizar Ali
  • Towards a Temporal Deep Learning Model to Support Sustainable Agricultural Practices.
  • Agustín García Pereira, Lukasz Porwol, Adegboyega Ojo and Edward Curry
  • Advanced Deep Learning Methodologies for Skin Cancer Classification in Prodromal Stages.
  • Muhammad Ali Farooq, Asma Khatoon, Viktor Varkarakis and Peter Corcoran
15:20 - 15:40 Coffee Break and Poster Session
15:40 - 16:40 Session 4 - AI and Reasoning Applications (Chair: Joeran Beel)
  • The Emotographic Iceberg: Exploring the Inferential Depths of Affective Computing.
  • Eoghan Furey and Juanita Blue
  • Investigating Company Logo Memorability with Convolutional Neural Embedding Models.
  • Eoghan Keany and James McDermott
  • Towards the Control of Epidemic Spread: Designing Reinforcement Learning Environments
  • Andrea Yanez, Conor Hayes and Frank Glavin
16:40 - 17:25 Keynote 1 – Prof. Heiko Paulheim, University of Mannheim, Germany (Chair: Michael Madden)

Beyond DBpedia & YAGO - The New Kids on the Knowledge Graph Block
Starting with Cyc in the 1980s, the collection of general knowledge in machine interpretable form has been considered a valuable ingredient in intelligent and knowledge intensive applications. Notable contributions in the field include the Wikipedia-based datasets DBpedia and YAGO, as well as the collaborative knowledge base Wikidata. Since Google has coined the term in 2012, they are most often referred to as knowledge graphs. Besides such open knowledge graphs, many companies have started using corporate knowledge graphs as a means of information representation. In this talk, I will look at two ongoing projects related to the extraction of knowledge graphs from Wikipedia and other Wikis. The first new dataset, CaLiGraph1, aims at the generation of explicit formal definitions from categories, and the extraction of new instances from list pages. In its current release, CaLiGraph contains 200k axioms defining classes, and more than 7M typed instances. In the second part, I will look at the transfer of the DBpedia approach to a multitude of arbitrary Wikis. The first such prototype, DBkWik2, extracts data from Fandom, a Wiki farm hosting more than 400k different Wikis on various topics. Unlike DBpedia, which relies on a larger user base for crowdsourcing an explicit schema and extraction rules, and the "one-page-per-entity" assumption, DBkWik has to address various challenges in the fields of schema learning and data integration. In its current release, DBkWik contains more than 11M entities, and has been found to be highly complementary to DBpedia.

17:25 - 17:30 Wrap Up (Chair: Edward Curry)
19:00

Conference Dinner (only open to confirmed dinner ticket-holders) Harbour Hotel

Google Maps


Schedule - Friday 6th December (Half Day)

09:00 - 09:10 Welcome (Chair: Edward Curry)
09:10 - 10:30 Session 5 - Understanding Data (Chair: Maraim Masoud)
  • A Topic-Based Approach to Multiple Corpus Comparison.
  • Jinghui Lu, Maeve Henchion and Brian Mac Namee
  • Analysis of Cryptocurrency Commodities with Motifs and LSTM.
  • Benjamin Barry and Martin Crane
  • Automatic Quantification of Knee Osteoarthritis Severity.
  • Jaynal Abedin, Joseph Antony, Kevin McGuinness, Kieran Moran, Noel E. O'Connor, Dietrich Rebholz-Schuhmann and John Newell
  • Detecting Hacker threats: Performance of word and sentence embedding models in identifying hacker communications.
  • Andrei Queiroz, Susan Mckeever and Brian Keegan
10:30 - 11:15 Keynote 2 - Prof. Barak A. Pearlmutter, Maynooth University, Ireland (Chair: Edward Curry)

Automatic Differentiation and Ubiquitous Adaptive Computing
Computer science has worked for decades to realize a sort of pantheistic dream, in which the inanimate objects that surround us are endowed with a vital computational essence and become our magical servants. The hardware is coming along nicely, but the vital essence is static: despite their remarkable abilities, our servants are bullheaded and unchanging. In order to make such complex systems adaptive, in a variety of senses, we need for adaptation to be compositional and automatic. As a step in that direction, we've tried to push a simple adaptive mechanism---gradient optimization---into fully general settings, complete with iteration and nesting and Turing equivalence. People now call this `differentiable programming'. I'll describe some of the automatic differentiation underpinnings that seem poised to help make the computers that surround us a bit less annoying.

11:15 - 11:40 Coffee Break and Poster Session
11:40 - 13:20 Session 6 - Speech, Video and Language (Chair: Rob Brennan)
  • Using Text Classification Methods to Detect Malware.
  • Quan Le, Eoghan Cunningham, Oisin Boydell, Benjamin Roques and Cormac Doherty
  • Back-translation Approach for Code-switching Machine Translation: A Case Study.
  • Maraim Masoud, Daniel Torregrosa, Mihael Arcan and Paul Buitelaar
  • NaïveRole: Author-Contribution Extraction and Parsing from Biomedical Manuscripts.
  • Dominika Tkaczyk, Andrew Collins and Joeran Beel
  • Perception Deception: Audio-Visual Mismatch in Virtual Reality Using The McGurk Effect.
  • Abubakr Siddig, Pheobe Sun, Matthew Parker and Andrew Hines
13:20 - 13.30 Closing Remarks (Chair: Brian Mac Namee)
13.30 Conference Close (Light Lunch)