Case-Based Reasoning and Deep Learning

Description
Recent advances in deep learning (DL) have helped to usher in a new wave of confidence in the capability of artificial intelligence. Increasingly, we are seeing DL architectures outperform long established state-of-the-art algorithms in a number of diverse tasks. In fact, DL has reached a point where it currently rivalsor has surpassed human performance in a number of challenges e.g. image classification, speech recognition and game play.
These successes of DL call for novel methods and techniques that exploit DL for the benefit of CBR systems. In particular, the potential of DL for CBR include improvement in knowledge aggregation and feature extraction for case representation, efficient indexing and retrieval architectures as well as assisting with case adaptation.

Workshop Goals
The goals of this workshop are to provide a forum to identify opportunities and challenges for the use of deep learning techniques and architectures in the context of case-based reasoning systems. Particular interests this workshop will explore include:

  • How DL can be used to improve knowledge aggregation strategies for case representation
  • The role of DL in making similarity computations easier and more efficient
  • Application of DL to help with solution adaptation
  • How DL architectures can be used to inspire more efficient indexing and retrieval architectures

Accordingly, we expect to draw interest from researchers from a number of related areas including Case-based Reasoning, Deep Learning and Machine Learning. We expect that this diversity would allow us to address the challenges in the field and identify where our efforts, as a research community, should focus.

Workshop Topics
Topics will include, but not limites to, the following:

  • Learning Theory;
  • Representation Learning;
  • Deep Learning Architechtures;
  • Hybrid Systems;
  • Deep Reinforcement Learning;
  • Deep Belief Networks;
  • Auto-encoders;
  • Feed-Forward Neural Networks;
  • Convolutional Neural Networks;
  • Recurrent Neural Networks;
  • Generative Adversarial Networks;
  • Transfer Learning and Domain Adaptation;
  • Similarity/Metric Learning Models;

Organisers
Kyle Martin (Co-Chair)
School of Computing Science and Digital Media
Sir Ian Wood Building
Robert Gordon University
AB10 7GJ
Aberdeen
United Kingdom
Email: k.martin@rgu.ac.uk
Tel: +44 1224 26 2553

Stelios Kapetanakis (Co-Chair)
School of Computing, Engineering and Mathematics
Cockroft Building
Lewes Road
BN2 4GJ
Brigthon
United Kingdom
Emai: s.kapetanakis@brighton.ac.uk
Tel: +44 1273 642563

Ajana Wijekoon
School of Computing Science and Digital Media
Sir Ian Wood Building
Robert Gordon University
AB10 7GJ
Aberdeen
United Kingdom
Email: a.wijekoon@rgu.ac.uk
Tel: +44 1224 26 2577

Kareem Amin
Smart Data & Knowledge Services Research Group
Case-based Reasoning Competence Center
German Research Center for Artificial Intelligence
Kaiserslautern
Germany
Email: kareem.amin@dfki.de
Tel: +49 177 519 0 349

Stewart Massie
School of Computing Science and Digital Media
Sir Ian Wood Building
Robert Gordon University
AB10 7GJ
Aberdeen
United Kingdom
Email: s.massie@rgu.ac.uk
Tel: +44 1224 26 2570