Personal profile

Overview

Epaminondas has spent many years in investigating ways to alleviate the tasks of interpreting, explaining and understandably communicating computational artefacts (e.g., algorithms, data, knowledge) with a variety of user types and personas.  Most noticeable stations of this explorative journey has been the design and implementation of a metadata driven visual query language, a human-computer interactive automaton and parser predicting user querying intention, a language and model for adaptive ontologies. His research culminated in prototypes being applicable to a variety of disciplines and real world projects such as retrieval of scientific and statistical databases for ozone hole research over the Arctic, natural language based querying and processing, as well as Web based decision trees as an e-consultation system in health care. Epaminondas did also apply Web and text mining techniques for competitive business intelligence within the context of Innovate UK funded initiative. Currently, Epaminondas is affiliated with the School of Physics, Engineering and Computer Science, University of Hertfordshire, UK, investigating human oriented explainable and interpretable AI/ML, such as natural language (conversational, dialogue) based systems and knowledge discovery from source code mining, as a contribution to responsible and trustworthy AI.

Research interests

  • Interpretable and Explainable AI
  • Self-explainable and Intelligible AI
  • AI Ethics
  • Interpretable and Explainable Data Science and Analytics
  • Algorithmic bias and debiasing (fairness)
  • Ethical Algorithmic Specification and Design
  • Source code analysis and knowledge extraction
  • Theory of Explanation, Meaning and Semantics
  • Cognitive processes for comprehension and explanation
  • Languages (spoken and sign) and conversational agents

Successfully completed MPhil/PhD supervisions:

  • A model for monolingual and cross-language retrieval driven by conceptual spaces (PhD, Diana Tanase, 2015)
  • Optimised meta-clustering approach for clustering Time Series Matrices (MPhil, Amir Motlagh, 2018)
  • External PhD examiner at Salford, Cranfield and NTNU (Norway) Universities

Teaching specialisms

  • Data Management and Science
  • Data and Knowledge Engineering
  • Algorithms
  • Web Intelligence
  • Artificial Intelligence
  • Machine Learning
  • Information Retrieval

Education/Academic qualification

Computer Science, PhD, MDDQL: A Meaning Driven Query Language, Swiss Federal Institute of Technology Zurich

1 Jan 19976 Apr 2001

Award Date: 6 Apr 2001

Computer Science, MSc, Providing explanations in deductive databases, Univ. of Karlsruhe

1 Apr 198831 Jul 1990

Award Date: 31 Jul 1992

Statistics and Informatics, BSc, Explaining statistical results to public stakeholders, University of Athens, Athens, Greece

1 Sept 198330 Sept 1987

Award Date: 30 Sept 1987

External positions

Full time academic staff member, The University of Westminster

17 Jan 200531 Jan 2021

Postdoc, Swiss Federal Institute of Technology Zurich

1 Jan 200230 Jun 2003

Reserch and teaching assistant, Swiss Federal Institute of Technology Zurich

1 Jan 199731 Dec 2001

Scientific project management, Forschungszentrum Karlsruhe GmbH FZK, Karlsruhe Institute of Technology, Inst Kernphys

1 Oct 199230 Jun 1997

Fingerprint

Dive into the research topics where Epameinondas Kapetanios is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
  • 1 Similar Profiles

Collaborations and top research areas from the last five years

Recent external collaboration on country/territory level. Dive into details by clicking on the dots or