I have recently started work on Machine Ethics. I am interested in how to implement and verify ethics in autonomous machines. Questions such as what kinds of ethics would autonomous machines agree to among themselves, how would we ensure that individually ethical machines don't combine to produce un-ethical behaviour, are interesting to pose and answer computationally. This is, by nature, an inter-disciplinary thread and I am quite interested in collaborating with folks in the field of philosophy/law/politics etc. I'm very interested in complex self-adaptive systems, engineering emergent feedback loops, predicting and controlling emergence in humano-tech systems (where technical systems interact heavily with human desires/abilities), engineering robust systems from non-robust parts. Multi-Agent Systems (MAS) are my preferred tool for approaching problems in self-adaptation, complexity, emergence, etc. They lend themselves to extensive forms of experimentation: having all agents follow simple rules, implementing complex machine-learning algorithms, investigating the interplay of different algorithms being used at the same time, are all possible with relatively simple conceptual structures. Decoding the end result and teasing out the real factor(s) responsible for a particular behaviour is considerably more difficult :-).
- BBSDelhi University
- Full-time Post-Graduate Diploma in Advanced Software TechnologyNational Centre for Software Technology
- Cert of CPD Univ Teaching & LearningUniversity College Dublin
- MSCarnegie Mellon University PA
- PhDUniversity of Birmingham
- Prof Cert University Teaching & LearningUniversity College Dublin