AICS 2020


The conference will be held online, Irish time (GMT+1). The detailed program is presented here to facilitate planning by participants and attendees. Each session is hosted in a Bongo virtual meeting which can be accessed by clicking in the headers of this programme.

Schedule – Monday 7th December (Full Day)

09:30 – 9:45Welcome (chair: Luca Longo)
09:45 – 10:30Keynote by Prof. Francesca Toni, Imperial College London, United Kingdom (chair: Luca Longo)

From Computational Argumentation to Explanation

Computational argumentation is a field in (symbolic AI) focusing on defining argumentation frameworks comprising sets of arguments and dialectical relations between them (e.g. of attack and, in addition or instead, of support), as well as so-called semantics (e.g. amounting to definitions of dialectically acceptable sets of arguments or of dialectical strength of arguments, satisfying desirable dialectical properties such as that supports against an argument should strengthen it). In this talk I will overview recent efforts deploying computational argumentation to obtain and deliver to users explanations of different formats for a variety of systems, including recommenders, classifiers and schedulers.
10:30-11:00Coffee Break
11:00-12:00Session 1 – Learning (chair: Arjun Pakrashi)

Active Learning for the Text Classification of Rock Climbing Logbook Data
Eoghan Cunningham and Derek Greene

TensorFlow enabled Deep Learning Model Optimization for enhanced Realtime Person Detection using Raspberry Pi operating at the Edge
Reenu Mohandas, Mangolika Bhattacharya, Mihai Penica, Martin Hayes and Karl Van Camp

Streetseek – Understanding Public Space Engagement Using Deep Learning & Thermal Imaging
Ciarán O’Mara and Eoghan Mulcahy
12:00-13:00Lunch Break
13:00-14:00Session 2 – Student track  1 (chair: Elizabeth Hunter)

Identifying Complaints from Product Reviews: A Case Study on Hindi
Raghvendra Pratap Singh, Rejwanul Haque, Mohammed Hasanuzzaman and Andy Way

Demand Prediction for Shared Mobility Services using Time Series Modelling
Rudi Camilleri and Jeremy Debattista

Optimising PID Control with Residual Policy Reinforcement Learning
Andrew Hynes, Ivana Dusparic and Elena Sapozhnikova

Synthesising Tabular Data using Wasserstein Conditional GANs with Gradient Penalty (WCGAN-GP)
Manhar Singh Walia, Brendan Tierney and Susan Mckeever

An Investigation of Transfer Learning for a Lifelog Dataset
Tejal Nijai, Akanksha Rajpute and Graham Healy

Neural Architecture Search using Particle Swarm and Ant Colony Optimization
Seamus Lankford and Diarmuid Grime
14:00-16:00Session 3 – AI applications (chair: Arjun Pakrashi)

LightGWAS: A Novel Machine Learning Procedure for Genome-Wide Association Study
Bruno Ambrozio, Luca Longo and Lucas Rizzo

Differentiation in Personality Emotion Mappings From Self Reported Emotion and Automatically Classified Emotion
Ryan Donovan, Ruairi O’Reilly and Aoife Johnson

Geoff: A Linked Data Vocabulary for Describing the Form and Function of Spatial Objects
Kristian McGlinn

An Evacuation Route Model for Disaster Affected Areas
Vinaysheel Kishor Wagh, Pramod Pathak, Paul Stynes and Luis Gustavo Nardin

Exploring Composite Dataset Biases for Heart Sound Classification
Davoud Shariat Panah, Andrew Hines and Susan Mckeever

Disenchantment with Emotion Recognition Technologies: A Comparison Between Humans Observers and Automatic Classifiers
Damien Dupré
16:00-16:30Coffee Break
16:30-18:00Session 4 – AI methods (chair: Lucas Rizzo)

Persistence pays off: Paying Attention to What the LSTM Gating Mechanism Persists
Giancarlo Salton and John Kelleher

KalmanTune: A Kalman filter based tuning method to make boosted ensembles robust to class-label noise
Arjun Pakrashi and Brian Mac Namee

Using Navigable Small Worlds to Speed Up Time-Series Classification
Vivek Mahato and Pádraig Cunningham

Combining Local Search and Genetic Algorithm for Two-Dimensional Guillotine Bin Packing Problems with partial sequence constraint
Filipe Souza and Diarmuid Grimes
18:00Wrap Up

Schedule – Tuesday 8th December (Half Day)

09:15-10:45Session 5 – Explainable AI and symbolic reasoning (chair: Elizabeth Hunter)

Incorporating Explainable Artificial Intelligence (XAI) to aid Understanding of Machine Learning in the Healthcare Domain
Urja Pawar, Donna O’Shea, Susan Rea and Ruairi O’Reilly

Exploring the potential of defeasible argumentation for quantitative inferences in real-world contexts: An assessment of computational trust
Lucas Rizzo, Pierpaolo Dondio and Luca Longo

A comparative analysis of rule-based, model-agnostic methods for explainable artificial intelligence
Giulia Vilone, Luca Longo and Lucas Rizzo
10:45-11:00Coffee break
11:00 – 12:15Session 6 – Student track 2 (chair: Luca Longo)

A Multi-class Approach – Building a Visual Classifier based on Textual Descriptions using Zero-Shot Learning
Preeti Jagdish Sajjan and Frank G Glavin

Less is More when Applying Transfer Learning to Multi-Spectral Data
Yuvraj Sharma and Robert Ross

Using GANs to Synthesise Minimum Training Data forDeepfake Generation
Simranjeet Singh, Rajneesh Sharma and Alan Smeaton

Intentional Forgetting: Investigating Interpretations and Future Potentials of Cognitive Control
Alysha Higgins

Analysis of Machine Learning Methods for Predicting Stock Prices
Oluwadurotimi Onibonoje, Kevin Djoussa and Mark Roantree

Improved Speech Synthesis using Generative Adversarial Networks
Dineshraj Gunasekaran, Gautham Venkatraj, Eoin Brophy and Tomas Ward

Simple Question Answering Over a Domain-Specific Knowledge Graph using BERT by Transfer Learning
Mani Vegupatti, Matthias Nickles and Bharathi Raja Chakravarthi
12:15-13:15Session 7 – AI, ethics and regulations  (chair: Lucas Rizzo)

Finding Short Lived Events on Social Media
David Kilroy, Simon Caton and Graham Healy

Assessing the Appetite for Trustworthiness and the Regulation of Artificial Intelligence in Europe
Labhaoise Nifhaolain, Andrew Hines and Vivek Nallur

Where’s the Why? In Search of Chains of Causes for Query Events
Suchana Datta, Derek Greene, Debasis Ganguly, Dwaipayan Roy and Mandar Mitra
13:15Closing Remarks and AIAI Community Meeting
Theme: Overlay by Kaira 
Technological University Dublin, Republic of Ireland