People
  1. Academic experts
  2. Research students
  3. Students
  4. Alumni
  5. Senior people at City
  6. Non-academic staff
  7. Honorary graduates
People

portrait of Alex (Aram) Ter-Sarkisov

Alex (Aram) Ter-Sarkisov

Lecturer in Artificial Intelligence

School of Mathematics, Computer Science and Engineering, Department of Computer Science

Contact Information

Contact

Visit Alex (Aram) Ter-Sarkisov

A309M, College Building

Postal Address

City, University of London
Northampton Square
London
EC1V 0HB
United Kingdom

About

Overview

My recent work is mostly on Deep Learning in Computer Vision (instance segmentation), but I'm also interested in Genetic Algorithms, both theory (mathematical analysis of runtime) and applications (new genetic operators). I like teaching machine learning, both at undergrad and advanced (ConvNets, FCNs, object detection/segmentation) levels.

Qualifications

  1. PhD, Massey University, New Zealand, 2012

Employment

  1. Postdoctoral Researcher, Dublin Institute of Technology, 2015 – 2018
  2. Postdoctoral Researcher, Universite du Maine, 2014 – 2015
  3. Postdoctoral Researcher, University of Waterloo, 2012 – 2013

Publications

  1. Ter-Sarkisov, A., Kelleher, J.D., Earley, B., Keane, M. and Ross, R.J. (2018). Beef Cattle Instance Segmentation Using Fully Convolutional Neural Network. British Machine Vision Conference 2018 3-7 September, Newcastle upon Tyne, UK.
  2. Ter-Sarkisov, A., Ross, R. and Kelleher, J. (2017). Bootstrapping Labelled Dataset Construction for Cow Tracking and Behavior Analysis. 2017 14th Conference on Computer and Robot Vision (CRV) 16-19 May, Edmonton, Canada.
  3. Ter-Sarkisov, A., Schwenk, H., Bougares, F. and Barrault, L. (2015). Incremental Adaptation Strategies for Neural Network Language Models. 3rd Workshop on Continuous Vector Space Models and their Compositionality 26-31 July, Beijing, China.
  4. Ter-Sarkisov, A., Marsland, S. and Holland, B. (2010). The K-bit-swap: A new genetic algorithm operator. 12th Annual conference on Genetic and Evolutionary Computation 7-11 July, Portland, Oregon.

Conference papers and proceedings (4)

  1. Ter-Sarkisov, A. (2012). Elitism levels traverse mechanism for the derivation of upper bounds on unimodal functions. 2012 IEEE Congress on Evolutionary Computation 10-15 June, Brisbane, Australia.
  2. Ter-Sarkisov, A. and Marsland, S. (2011). Convergence of a recombination-based elitist evolutionary algorithm on the royal roads test function. 24th Australasian Joint Conference on Artificial Intelligence, AI 2011 5-8 December, Perth, Australia.
  3. Ter-Sarkisov, A. and Marsland, S. (2011). Convergence properties of two (μ+λ) Evolutionary Algorithms on onemax and royal roads test functions. 3rd International Joint Conference on Computational Intelligence 24-26 October, Paris, France.
  4. Ter-Sarkisov, A. and Marsland, S. (2011). Convergence properties of (μ + λ) evolutionary algorithms. Twenty-Fifth AAAI Conference on Artificial Intelligence 7-11 August, San Francisco.

Journal article

  1. Ter-Sarkisov, A. and Marsland, S. (2017). K-Bit-Swap: a new operator for real-coded evolutionary algorithms. Soft Computing, 21(20), pp. 6133–6142. doi:10.1007/s00500-016-2170-6.

Thesis/dissertation

  1. Ter-Sarkisov, A. Computational complexity of elitist population-based evolutionary algorithms : a thesis presented in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Computer Science at Massey University, Palmerston North, New Zealand. (PhD Thesis)