• Publications
  • Influence
The SeqWord Genome Browser: an online tool for the identification and visualization of atypical regions of bacterial genomes through oligonucleotide usage
tl;dr
The SeqWord Genome Browser (SWGB) was developed to visualize the natural compositional variation of DNA sequences. Expand
  • 45
  • 4
  • Open Access
Measuring Saturation in Neural Networks
tl;dr
In the neural network context, the phenomenon of saturation refers to the state in which a neuron predominantly outputs values close to the asymptotic ends of the bounded activation function. Expand
  • 9
  • 2
  • Open Access
Cooperative charged particle swarm optimiser
tl;dr
This paper investigates the performance of a cooperative version of the charged PSO on a benchmark of dynamic optimisation problems. Expand
  • 13
  • 1
Weight regularisation in particle swarm optimisation neural network training
tl;dr
We propose adding a weight regularisation penalty term to the objective function of the PSO in order to improve NN training. Expand
  • 7
  • 1
Training neural networks with PSO in dynamic environments
tl;dr
This paper investigates the applicability of dynamic PSO to NN training in changing environments.Supervised neural networks have to be adapted to track the changing decision boundaries and detect new boundaries as they appear. Expand
  • 23
Training feedforward neural networks with dynamic particle swarm optimisation
tl;dr
This paper investigates the applicability of dynamic particle swarm optimisation algorithms as neural network training algorithms under the presence of concept drift. Expand
  • 21
Analysis of error landscapes in multi-layered neural networks for classification
tl;dr
We use fitness landscape analysis to quantify topological properties of neural network error landscapes, and apply it to architecture selection. Expand
  • 8
Training high-dimensional neural networks with cooperative particle swarm optimiser
tl;dr
This paper analyses the behaviour of particle swarm optimisation applied to training high-dimensional neural networks. Expand
  • 6
Saturation in PSO neural network training: Good or evil?
tl;dr
We studied the influence of weight initialisation range, maximum velocity, and search space boundaries on the degree of saturation in particle swarm optimisation as a neural network training algorithm. Expand
  • 10
Using particle swarm optimisation to train feedforward neural networks in dynamic environments
The feedforward neural network (NN) is a mathematical model capable of representing any non-linear relationship between input and output data. It has been succesfully applied to a wide variety ofExpand
  • 2