Foundations of Machine Learning Systems

We specialise in designing, developing, and implementing state-of-the-art machine learning systems and foundational algorithms, tailored to address practical challenges across various sectors.

Overview

Our focus extends to addressing many of the shortcomings of contemporary AI approaches, such as the black-box nature and the brittleness of deep learning. Our expertise covers:

artificial neural networks
neural architecture search
feature selection/engineering
federated learning
fuzzy systems
optimisation algorithms
parallel computation
reinforcement learning
generative models, and more.

We have successfully applied these techniques to real-world problems in agriculture, biomedicine, cyber security, healthcare, transportation, remote sensing and robotics.

Meet the team

Dr Xiaowei Gu

Senior Lecturer

Dr Amir Esfahani

Associate Professor in Robotics

Professor Ferrante Neri

Professor of Machine Learning and Artificial Intelligence, Associate Dean (international) FEPS, Head of the Nature Inspired Computing and Engineering Research Group

Dr Lu Yin

Assistant Professor in AI

Dr Pedro Porto Buarque De Gusmao

Lecturer in Computer Science

Dr Roman Bauer

Senior Lecturer

Dr Xilu Wang

Surrey Future Fellow

Selected publications

Y. Xue, X. Han, F. Neri, Q. Jiafeng, D. Pelusi, "A gradient-guided evolutionary neural architecture search", IEEE Transactions on Neural Networks and Learning Systems, 2024 (to appear). https://doi.org/10.1109/TNNLS.2024.3371432
Y. Xue, W. Tong, F. Neri, P. Chen, T. Luo, L. Zhen, X. Wang, "Evolutionary architecture search for generative adversarial networks based on weight sharing", IEEE Transactions on Evolutionary Computation vol. 28, no. 3, pp: 653-667, 2024. https://doi.org/10.1109/TEVC.2023.3338371
G. Li, L. Yin, J. Ji, W. Niu, M. Qin, B. Ren, L. Guo, S. Liu, X. Ma. "NeurRev: Train better sparse neural network practically via neuron revitalization", International Conference on Learning Representations, pp. 1-16, 2024. https://openreview.net/pdf?id=60lNoatp7u
L. Yin, Y. Wu, Z. Zhang, C. Hsieh, Y. Wang, Y. Jia, M. Pechenizkiy, Y. Liang, Z. Wang, S. Liu. "Outlier weighed layerwise sparsity (owl): A missing secret sauce for pruning llms to high sparsity." International Conference on Machine Learning, pp. 1-15, 2024. https://openreview.net/pdf?id=ahEm3l2P6w
Y. Rehman, Y. Gao, P. Gusmao, M. Alibeigi, J. Shen, N. Lane. "L-dawa: Layer-wise divergence aware weight aggregation in federated self-supervised visual representation learning", IEEE/CVF International Conference on Computer Vision, pp. 16418-16427, 2023. https://doi.org/10.1109/ICCV51070.2023.01509
X. Wang, Y. Jin, S. Schmitt, M. Olhofer, "Alleviating search bias in Bayesian evolutionary optimization with many heterogeneous objectives," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 54, no. 1, pp. 143-155, 2024. https://doi.org/10.1109/TSMC.2023.3306085
H. Zhu, X. Wang, Y. Jin, "Federated many-task Bayesian optimization", IEEE Transactions on Evolutionary Computation, vol. 28, no. 4, pp: 980-993, 2024. https://doi.org/10.1109/TEVC.2023.3279775
X. Gu, P. Angelov, J. Han, Q. Shen, "Multilayer evolving fuzzy neural networks", IEEE Transactions on Fuzzy Systems, vol. 31, no. 12, pp. 4158-4169, 2023. https://doi.org/10.1109/TFUZZ.2023.3276263
X. Gu, P. Angelov, Q. Shen. "Semi-supervised fuzzily weighted adaptive boosting for classification", IEEE Transactions on Fuzzy Systems, vol. 32, no. 4, pp: 2318-2330, 2024. https://doi.org/10.1109/TFUZZ.2024.3349637

Funded Projects

FAPESP (São Paulo Research Foundation) SPRINT Project “Neuro-GEMA: A Grammar-based Evolutionary Method to Automatically Design Flexible Convolutional Neural Networks”. Leading Scientist: F. Neri, 2023-2025

Other Achievements:

F. Neri, since 2019 to present World's Top 2% Scientists by Stanford University.