Edinburgh Research Explorer

Dr Oisin Mac Aodha

Lecturer in Machine Learning

Research Interests

My research interests are broadly in the areas of machine learning and computer vision. I am particularly interested in questions related to human-in-the-loop machine learning with the aim of creating next-generation methods that take advantage of the complementary strengths of humans and machines. This involves the development of new models and algorithms for interacting with communities of experts to enable solutions for problems such as computer assisted teaching, interpretable representation learning, and applications such as biodiversity monitoring.

Biography

Oisin Mac Aodha received a BEng in Electronic and Computing Engineering from the National University of Ireland Galway in 2007. He then went on to receive an MSc in Machine Learning from the University College of London (UCL) in 2008 and afterwards spent one year as a research assistant at ETH Zurich. He was awarded an NUI Travelling Studentship in the Sciences in 2010 and subsequently obtained a PhD in Computer Science from UCL in 2014 under the supervision of Prof. Gabriel Brostow. After his PhD he was a postdoc at UCL working on interactive machine learning methods for efficient biodiversity monitoring. Between 2016 and 2019 he was a postdoc at the California Institute of Technology working with Prof. Pietro Perona. In 2019 he started as a Lecturer in Machine Learning in the School of Informatics at the University of Edinburgh.

Qualifications

BEng Electronic and Computing Engineering, National University of Ireland Galway, 2003-2007
MSc Machine Learning, University College London, 2007-2008
PhD Computer Science, University College London, 2010-2014

Research outputs

  1. Teaching Multiple Concepts to a Forgetful Learner

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  2. Digging Into Self-Supervised Monocular Depth Estimation

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  3. Presence-Only Geographical Priors for Fine-Grained Image Classification

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

View all (23) »

ID: 118297184