Harith Al-Sahaf

TL;DR: This paper provides a review on evolutionary machine learning techniques for major machine learning tasks such as classification, regression and clustering, and emerging topics including combinatorial optimisation, computer vision, deep learning, transfer learning, and ensemble learning.

TL;DR: A novel approach based on transfer learning and GP to solve complex image classification problems by extracting and reusing blocks of knowledge/information automatically discovered from similar as well as different image classification tasks during the evolutionary process achieves better classification performance than the state-of-the-art image classification algorithm.

TL;DR: A novel genetic programming-based method that automatically synthesises a descriptor using only two training instances per class is proposed that is robust to rotation and has significantly outperformed, or achieved a comparable performance to, the baseline methods.

TL;DR: This method is compared with feature based image classification by GP and another GP method which also aims to automatically extract image features, and the results show that the highest accuracies are achieved by Two-Tier GP.

TL;DR: Genetic programming is utilized to automatically construct a rotation-invariant image descriptor by synthesizing a set of formulas using simple arithmetic operators and first-order statistics, and determining the length of the feature vector simultaneously using only two instances per class.