Biography
Tim is a PhD student researching,
- Uncertainty in neural networks (NNs) / deep learning
- Bayesian NNs, ensembled NNs, Gaussian Processes.
- Uncertainty in Reinforcement Learning.
- Applications of the above to manufacturing data.
He spent one year as an exchange student at the Alan Turing Institute.
Background
Tim completed an M.Eng at Durham University, his masters thesis developed a creative AI. He has work experience in the finance sector with EY, with whom he qualified as a Chartered Accountant. His work was focused around analytics and building forecasting models to support decision making.
Publications
High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach (https://arxiv.org/abs/1802.07167), ICML 2018
Bayesian Inference with Anchored Ensembles of Neural Networks, and Application to Exploration in Reinforcement Learning (https://arxiv.org/abs/1805.11324), Exploration in Reinforcement Learning Workshop ICML 2018
Bayesian Neural Network Ensembles (https://arxiv.org/abs/1811.12188), Bayesian Deep Learning Workshop NeurIPS (NIPS) 2018
Expressive Priors in Bayesian Neural Networks: Kernel Combinations and Periodic Functions (https://arxiv.org/abs/1905.06076), Uncertainty in Artificial Intelligence (UAI) 2019
