Neural Networks

The Multilayer Perceptron is a classic Artificial Neural Network that was popular in the 1990s. It uses a layer of hidden units each of which bipartitions 'input space' into distinct regions (see straight lines in Figure below). An output layer, comprising a sigmoidal function, can then combine these partitions into an arbitrarily complex response function (see dark versus light regions below). The number of hidden units can be selected using Bayesian model comparison.

This work was in collaboration with Steve Roberts and Dirk Husmeier.

• D. Husmeier, W.D. Penny, and S.J. Roberts. An empirical evaluation of Bayesian sampling with hybrid Monte Carlo for training neural network classifiers. Neural Networks, 12:677-705, 1999.

• W.D. Penny and S.J. Roberts. Bayesian neural networks for classification: how useful is the evidence framework ? Neural Networks, 12:877-892, 1998. PDF

• W.D. Penny and D. Frost. Neural networks in clinical medicine. Medical Decision Making, 16(4):386-398, 1996. PDF

• S.J. Roberts and W.D. Penny. Neural networks: friends or foes ? Sensor Review, 17(1):64-70, 1996.