Cooperative charged particle swarm optimiser
A. Rakitianskaia, A. Engelbrecht, "Cooperative charged particle swarm optimiser." In the proceedings of IEEE Congress on Evolutionary Computation, 2008.
CV
Education
- B.Sc in Computer Science, University of Pretoria, 2006
- B.Sc (Hons) in Computer Science, University of Pretoria, 2007
- M.Sc in Computer Science, University of Pretoria, 2012
- Ph.D in Computer Science, University of Pretoria, 2019
Work experience
- October 2006 - December 2008: Junior Programmer
- Department of Biochemistry, University of Pretoria, Pretoria, South Africa
- Developed a web-based genome visualizer based on existing Python code
- June 2012 - October 2013: Junior Researcher
- Joint Institute for Nuclear Research, Dubna, Russia
- Worked on neural network applications to chaotic time series analysis
- January 2014 - December 2020: Lecturer; January 2021 - present: Senior Lecturer
- University of Pretoria, Pretoria, South Africa
- Courses taught:
- Introduction to Procedural Programming (C)
- Introduction to Object-Oriented Programming (C++)
- Algorithms and Data Structures (Java)
- Artificial Intelligence (Honours course with a heavy focus on neural networks and deep learning)
- Introduction to Machine Learning (Masters course)
Publications
Training neural networks with PSO in dynamic environments
A. Rakitianskaia, A. Engelbrecht, "Training neural networks with PSO in dynamic environments." In the proceedings of IEEE Congress on Evolutionary Computation, 2009.
Training feedforward neural networks with dynamic particle swarm optimisation
Anna Rakitianskaia, Andries Engelbrecht, "Training feedforward neural networks with dynamic particle swarm optimisation." Swarm Intelligence, 2012.
Training high-dimensional neural networks with cooperative particle swarm optimiser
A. Rakitianskaia, A. Engelbrecht, "Training high-dimensional neural networks with cooperative particle swarm optimiser." In the proceedings of International Joint Conference on Neural Networks, 2014.
Weight regularisation in particle swarm optimisation neural network training
A. Rakitianskaia, A. Engelbrecht, "Weight regularisation in particle swarm optimisation neural network training." In the proceedings of IEEE Symposium on Swarm Intelligence, 2014.
Measuring saturation in neural networks
A. Rakitianskaia, A. Engelbrecht, "Measuring saturation in neural networks." In the proceedings of IEEE Symposium Series on Computational Intelligence, 2015.
Saturation in PSO Neural Network Training: Good or Evil?
A. Rakitianskaia, A. Engelbrecht, "Saturation in PSO Neural Network Training: Good or Evil?." In the proceedings of IEEE Congress on Evolutionary Computation, 2015.
Analysis of error landscapes in multi-layered neural networks for classification
A. Rakitianskaia, Eduan Bekker, Katherine Malan, A. Engelbrecht, "Analysis of error landscapes in multi-layered neural networks for classification." In the proceedings of IEEE Congress on Evolutionary Computation, 2016.
Search space boundaries in neural network error landscape analysis
Anna Bosman, Andries Engelbrecht, Marde Helbig, "Search space boundaries in neural network error landscape analysis." In the proceedings of IEEE Symposium Series on Computational Intelligence, 2016.
Characterising neutrality in neural network error landscapes
Willem Aardt, Anna Bosman, Katherine Malan, "Characterising neutrality in neural network error landscapes." In the proceedings of IEEE Congress on Evolutionary Computation, 2017.
Fitness Landscape Analysis of Weight-Elimination Neural Networks
Anna Bosman, Andries Engelbrecht, Mard{\'e} Helbig, "Fitness Landscape Analysis of Weight-Elimination Neural Networks." Neural Processing Letters, 2018.
Progressive gradient walk for neural network fitness landscape analysis
Anna Bosman, Andries Engelbrecht, Marde Helbig, "Progressive gradient walk for neural network fitness landscape analysis." In the proceedings of Genetic and Evolutionary Computation Conference Companion, 2018.
Evolutionary Neural Architecture Search for Image Restoration
Gerard Wyk, Anna Bosman, "Evolutionary Neural Architecture Search for Image Restoration." In the proceedings of IEEE International Joint Conference on Neural Networks, 2019.
Unsupervised Change Detection in Satellite Images Using Convolutional Neural Networks
Kevin Jong, Anna Bosman, "Unsupervised Change Detection in Satellite Images Using Convolutional Neural Networks." In the proceedings of IEEE International Joint Conference on Neural Networks, 2019.
Visualising Basins of Attraction for the Cross-Entropy and the Squared Error Neural Network Loss Functions
Anna Bosman, Andries Engelbrecht, Mard{\'e} Helbig, "Visualising Basins of Attraction for the Cross-Entropy and the Squared Error Neural Network Loss Functions." arXiv e-prints, 2019.
Fitness Landscape Analysis of Feed-Forward Neural Networks
Anna Sergeevna Bosman, "Fitness Landscape Analysis of Feed-Forward Neural Networks." PhD Thesis, University of Pretoria, South Africa, 2019.
Black-box saliency map generation using Bayesian optimisation
Mamuku Mokuwe, Michael Burke, Anna Bosman, "Black-box saliency map generation using Bayesian optimisation." In the proceedings of International Joint Conference on Neural Networks (IJCNN), 2020.
Loss surface modality of feed-forward neural network architectures
Anna Bosman, Andries Engelbrecht, Mard{\'e} Helbig, "Loss surface modality of feed-forward neural network architectures." In the proceedings of International Joint Conference on Neural Networks (IJCNN), 2020.
Visualising basins of attraction for the cross-entropy and the squared error neural network loss functions
Anna Bosman, Andries Engelbrecht, Mard{\'e} Helbig, "Visualising basins of attraction for the cross-entropy and the squared error neural network loss functions." Neurocomputing, 2020.
Analysing the loss landscape features of generative adversarial networks
Jarrod Moses, Katherine Malan, Anna Bosman, "Analysing the loss landscape features of generative adversarial networks." In the proceedings of Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2021.
Characterisation of environment type and difficulty for streamed data classification problems
Mathys Ellis, Anna Bosman, Andries Engelbrecht, "Characterisation of environment type and difficulty for streamed data classification problems." Information Sciences, 2021.
Hybridised loss functions for improved neural network generalisation
Matthew Dickson, Anna Bosman, Katherine Malan, "Hybridised loss functions for improved neural network generalisation." In the proceedings of Pan-African Artificial Intelligence and Smart Systems Conference, 2021.
A Local Optima Network Analysis of the Feedforward Neural Architecture Space
Isak Potgieter, Christopher Cleghorn, Anna Bosman, "A Local Optima Network Analysis of the Feedforward Neural Architecture Space." In the proceedings of International Joint Conference on Neural Networks (IJCNN), 2022.
ATLAS: Universal Function Approximator for Memory Retention
Heinrich Deventer, Anna Bosman, "ATLAS: Universal Function Approximator for Memory Retention." arXiv preprint arXiv:2208.05388, 2022.
Cauchy Loss Function: Robustness Under Gaussian and Cauchy Noise
Thamsanqa Mlotshwa, Heinrich Deventer, Anna Bosman, "Cauchy Loss Function: Robustness Under Gaussian and Cauchy Noise." In the proceedings of Artificial Intelligence Research: Third Southern African Conference, 2022.
Convolutional neural networks for crack detection on flexible road pavements
Hermann Tapamo, Anna Bosman, James Maina, Emile Horak, "Convolutional neural networks for crack detection on flexible road pavements." In the proceedings of International Conference on Soft Computing and Pattern Recognition, 2022.
Genetic Micro-Programs for Automated Software Testing with Large Path Coverage
Jarrod Goschen, Anna Bosman, Stefan Gruner, "Genetic Micro-Programs for Automated Software Testing with Large Path Coverage." In the proceedings of IEEE Congress on Evolutionary Computation (CEC), 2022.
KASAM: Spline Additive Models for Function Approximation
Heinrich Deventer, Pieter Rensburg, Anna Bosman, "KASAM: Spline Additive Models for Function Approximation." arXiv preprint arXiv:2205.06376, 2022.
Denoising Diffusion Post-Processing for Low-Light Image Enhancement
Savvas Panagiotou, Anna Bosman, "Denoising Diffusion Post-Processing for Low-Light Image Enhancement." arXiv preprint arXiv:2303.09627, 2023.
Training Feedforward Neural Networks with Bayesian Hyper-Heuristics
Arn{\'e} Schreuder, Anna Bosman, Andries Engelbrecht, Christopher Cleghorn, "Training Feedforward Neural Networks with Bayesian Hyper-Heuristics." arXiv preprint arXiv:2303.16912, 2023.