List of publications:
Dufourq, E., Durbach, Ian and Hansford, James and Hoepfner, Amanda and Ma, Heidi and Bryant, Jessica and Stender, Christina and Li, Wenyong and Liu, Zhiwei and Chen, Qing and Zhou, Zhaoli and Turvey, Samuel. (2021). Automated detection of Hainan gibbon calls for passive acoustic monitoring. Remote sensing in ecology and conservation. [Paper]
Dufourq, E., Facial Expression Recognition using Convolutional Neural Networks, SAICSIT 2020, South Africa [Paper]
Dufourq, E., Bassett, B. A., Evolutionary Facial Expression Recognition, SAICSIT 2020, South Africa [Paper]
Dufourq, E., Bassett, B. A., EDEN: Evolutionary Deep Networks for Efficient Machine Learning, PRASA-ROBMECH 2017, South Africa [Paper]
Dufourq, E., Bassett, B. A., Text Compression for Sentiment Analysis via Evolutionary Algorithms, PRASA-ROBMECH 2017, South Africa [Paper]
Dufourq, E., Bassett, B. A., Automated Classification of Text Sentiment, SAICSIT 2017, South Africa [Paper]
Dufourq, E., Bassett, B. A., Automated Problem Identification: Regression vs Classification via Evolutionary Deep Networks, SAICSIT 2017, South Africa [Paper]
Dufourq, E., Pillay, N., Hybridizing Evolutionary Algorithms for Creating Classi er Ensembles, Sixth World Congress on Nature and Biologically Inspired Computing, Portugal 2014 [Paper]
Dufourq, E., Pillay, N., Incorporating Adaptive Discretization into Genetic Programming for Data Classi cation, Third World Congress on Information and Communication Technologies, Vietnam 2013. [Paper]
Dufourq, E.,Pillay, N., A Preliminary Study on the Reuse of Subtrees Within Decision Trees in a Genetic Programming Context for Data Classi cation, Third World Congress on Information and Communication Technologies, Vietnam 2013. [Paper]
Dufourq, E.,Pillay, N., A Comparison of Genetic Programming Representations for Binary Data Classi cation, Third World Congress on Information and Communication Technologies, Vietnam 2013. [Paper]
Dufourq, E., Olusanya, M.O. and Adewumi, A., Studies in metaheuristics for the Blood Assignment Problem, 41st Annual Conference of the Operations Research Society of South Africa, South Africa 2012.
N Jacobs, M Quayle, E Dufourq, K Durrheim., The development and validation of an adjacency segregation analyzer, International Journal of Psychology 47, 2012.
PhD thesis titled Evolutionary Deep Learning, abstract:
The primary objective of this thesis is to investigate whether evolutionary concepts can improve the performance, speed and convenience of algorithms in various active areas of machine learning research. Deep neural networks are exhibiting an explosion in the number of parameters that need to be trained, as well as the number of permutations of possible network architectures and hyper-parameters. There is little guidance on how to choose these and brute-force experimentation is prohibitively time consuming. We show that evolutionary algorithms can help tame this explosion of freedom, by developing an algorithm that robustly evolves near optimal deep neural network architectures and hyper-parameters across a wide range of image and sentiment classification problems. We further develop an algorithm that automatically determines whether a given data science problem is of classification or regression type, successfully choosing the correct problem type with more than 95% accuracy. Together these algorithms show that a great deal of the current “art” in the design of deep learning networks – and in the job of the data scientist – can be automated. Having discussed the general problem of optimising deep learning networks the thesis moves on to a specific application: the automated extraction of human sentiment from text and images of human faces. Our results reveal that our approach is able to outperform several public and/or commercial text sentiment analysis algorithms using an evolutionary algorithm that learned to encode and extend sentiment lexicons. A second analysis looked at using evolutionary algorithms to estimate text sentiment while simultaneously compressing text data. An extensive analysis of twelve sentiment datasets reveal that accurate compression is possible with 3.3% loss in classification accuracy even with 75% compression of text size, which is useful in environments where data volumes are a problem. Finally, the thesis presents improvements to automated sentiment analysis of human faces to identify emotion, an area where there has been a tremendous amount of progress using convolutional neural networks. We provide a comprehensive critique of past work, highlight recommendations and list some open, unanswered questions in facial expression recognition using convolutional neural networks. One serious challenge when implementing such networks for facial expression recognition is the large number of trainable parameters which results in long training times. We propose a novel method based on evolutionary algorithms, to reduce the number of trainable parameters whilst simultaneously retaining classification performance, and in some cases achieving superior performance. We are robustly able to reduce the number of parameters on average by 95% with no loss in classification accuracy. Overall our analyses show that evolutionary algorithms are a valuable addition to machine learning in the deep learning era: automating, compressing and/or improving results significantly, depending on the desired goal.
Masters thesis titled Data Classication using Genetic Programming