Edinburgh Research Explorer

Institute for Adaptive and Neural Computation

Organisational unit: Research Institute

  1. Modelling mechanotransduction in primary sensory endings

    Suslak, T., McKay-Fletcher, J. A., Armstrong, D., Jarman, A. & Bewick, G., 2013.

    Research output: Contribution to conferencePoster

  2. A model of mechanotransduction in Drosophila non-ciliated, primary endings

    Suslak, T., Bewick, G., Armstrong, D. & Jarman, A., 2013.

    Research output: Contribution to conferencePoster

  3. A model of mechanotransduction in Drosophila non-ciliated, primary endings

    Suslak, T., McKay-Fletcher, J. A., Bewick, G., Armstrong, D. & Jarman, A., 2013.

    Research output: Contribution to conferencePoster

  4. Piecewise Pseudolikelihood for Efficient Training of Conditional Random Fields

    Sutton, C. & McCallum, A., 2007, Proceedings of the 24th International Conference on Machine Learning. New York, NY, USA: ACM, p. 863-870 8 p.

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

  5. Dynamic Conditional Random Fields: Factorized Probabilistic Models for Labeling and Segmenting Sequence Data

    Sutton, C., McCallum, A. & Rohanimanesh, K., 1 May 2007, In : Journal of Machine Learning Research. 8, p. 693-723 31 p.

    Research output: Contribution to journalArticle

  6. An Introduction to Conditional Random Fields

    Sutton, C. & McCallum, A., 2012, In : Foundations and Trends in Machine Learning. 4, 4, p. 267-373 109 p.

    Research output: Contribution to journalArticle

  7. Piecewise training for structured prediction

    Sutton, C. & McCallum, A., Dec 2009, In : Machine Learning. 77, 2-3, p. 165-194 30 p.

    Research output: Contribution to journalArticle

  8. Local Training and Belief Propagation

    Sutton, C. & Minka, T., Aug 2006, Microsoft Research, 10 p. (Microsoft Research Technical Reports; no. MSR-TR-2006-121).

    Research output: Working paper