If you made any changes in Pure these will be visible here soon.

Personal profile

Research interests

Biologically inspired algorithms, neural networks and optimisation of their topologies

Fingerprint Dive into the research topics where Alan Thomas is active. These topic labels come from the works of this person. Together they form a unique fingerprint.

  • 1 Similar Profiles

Network Recent external collaboration on country level. Dive into details by clicking on the dots.

Research Output

  • 3 Conference contribution with ISSN or ISBN
  • 2 Article

Developing a risk stratification tool for audit of outcome after surgery for head and neck squamous cell carcinoma

Tighe, D. F., Thomas, A. J., Sassoon, I., Kinsman, R. & McGurk, M., 29 Mar 2017, In : Head and Neck. 39, 7, p. 1357-1363 7 p.

Research output: Contribution to journalArticle

  • Two Hidden Layers are Usually Better than One

    Thomas, A., Petridis, M., Walters, S., Malekshahi Gheytassi, M. & Morgan, R., 2 Aug 2017, EANN: International Conference on Engineering Applications of Neural Networks. Switzerland: Springer International Publishing, Vol. 744. p. 279-290 12 p. (Communications in Computer and Information Sciences).

    Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBN

    Open Access
    File
  • Accelerated Optimal Topology Search for Two-hidden-layer Neural Networks

    Thomas, A., Walters, S., Petridis, M., Malekshahi Gheytassi, M. & Morgan, R., 19 Aug 2016, Engineering Applications of Neural Networks. EANN 2016. Switzerland: Springer International Publishing, p. 253-266 14 p. (Communications in Computer and Information Sciences).

    Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBN

    Open Access
    File
  • On the Optimal Node Ratio between Hidden Layers: A Probabilistic Study

    Thomas, A., Walters, S., Malekshahi Gheytassi, M., Morgan, R. & Petridis, M., 7 Oct 2016, In : International Journal of Machine Learning and Computing. 6, 5, p. 241-247 7 p.

    Research output: Contribution to journalArticle

    Open Access
    File
  • On predicting the optimal number of hidden nodes

    Thomas, A., Petridis, M., Walters, S., Malekshahi Gheytassi, M. & Morgan, R., 8 Dec 2015, 2015 international conference on computational science and computational intelligence. Las Vegas: CPS/IEEE, p. 565-570 6 p.

    Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBN