• Publications
  • Influence
Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation
TLDR
We propose Deep Reconstruction-Classification Network (DRCN), a convolutional network that jointly learns two tasks: i) supervised source label prediction and ii) unsupervised target data reconstruction. Expand
  • 391
  • 43
  • PDF
Particle Swarm Optimization for Feature Selection in Classification: A Multi-Objective Approach
TLDR
We investigate two PSO-based multi-objective feature selection algorithms based on the idea of nondominated sorting into PSO to address feature selection problems. Expand
  • 633
  • 36
  • PDF
Domain Generalization for Object Recognition with Multi-task Autoencoders
TLDR
The problem of domain generalization is to take knowledge acquired from a number of related domains, where training data is available, and to then successfully apply it to previously unseen domains. Expand
  • 233
  • 35
  • PDF
Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization
TLDR
We propose Scatter Component Analyis (SCA), a fast representation learning algorithm that can be applied to both domain adaptation and domain generalization. Expand
  • 161
  • 31
  • PDF
A Survey on Evolutionary Computation Approaches to Feature Selection
TLDR
Feature selection is an important task in data mining and machine learning to reduce the dimensionality of the data and increase the performance of an algorithm. Expand
  • 636
  • 30
  • PDF
Particle swarm optimisation for feature selection in classification: Novel initialisation and updating mechanisms
TLDR
We propose three new initialisation strategies and three new personal best and global best updating mechanisms in PSO to develop novel feature selection approaches with the goals of maximising the classification performance, minimising the number of features and reducing the computational time. Expand
  • 292
  • 24
  • PDF
Cooperative coevolution of Elman recurrent neural networks for chaotic time series prediction
TLDR
This work employs two problem decomposition methods for training Elman recurrent neural networks on chaotic time series prediction. Expand
  • 160
  • 10
  • PDF
Developing New Fitness Functions in Genetic Programming for Classification With Unbalanced Data
TLDR
We develop several new fitness functions for binary classification with unbalanced data. Expand
  • 83
  • 10
  • PDF
A Domain-Independent Window Approach to Multiclass Object Detection Using Genetic Programming
TLDR
This paper describes a domain-independent approach to the use of genetic programming for object detection problems in which the locations of small objects of multiple classes in large images must be found. Expand
  • 142
  • 9
Evolving Deep Convolutional Neural Networks for Image Classification
TLDR
We propose a new method using genetic algorithms for evolving the architectures and connection weight initialization values of a deep convolutional neural network to address image classification problems. Expand
  • 108
  • 9
  • PDF