Mr Tim Pearce

Contact information

Research interests

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.

Publications

Pearce, T., Zaki, M., Brintrup, A., & Neely, A. (2019). Uncertainty in Neural Networks: Bayesian Ensembling. Under Review.

Pearce, T., Zaki, M., Brintrup, A., & Neely, A. (2018). Bayesian Neural Network Ensembles. Bayesian Deep Learning Workshop, NeurIPS (NIPS).

Pearce, T., Zaki, M., Brintrup, A., & Neely, A. (2018). High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach. In Proceedings of the 35th International Conference on Machine Learning, ICML. Stockholm.

Pearce, T., Anastassacos, N., Zaki, M., & Neely, A. (2018). Bayesian Inference with Anchored Ensembles of Neural Networks, and Application to Exploration in Reinforcement Learning. In Exploration in Reinforcement Learning Workshop, ICML. Stockholm.

Palau, A. S., Bakliwal, K., Dhada, M. H., Pearce, T., & Parlikad, A. K. (2018). Recurrent Neural Networks for real-time distributed collaborative prognostics. In IEEE International Conference on Prognostics and Health Management (ICPHM).

About us

The Cambridge Centre for Data-Driven Discovery (C2D3) brings together researchers and expertise from across the academic departments and industry to drive research into the analysis, understanding and use of data science.

The Centre is funded by a series of collaborations with partners in business and industry which have an interest in using data science for the benefit of their customers and their organisations. Our founding partner is Aviva, the UK’s leading insurance company. We work with industrial partners to build a portfolio of collaborative research projects, provide professional development opportunities for their own staff and access to the full breadth and depth of the University’s talent pool in the area of data science.

With unprecedented access to increasing volumes of data, our research ranges from the underlying fundamentals in mathematics and computer science, to data science applications across all six University Schools of Arts and Humanities, Biological Sciences, Clinical Medicine, Humanities and Social Sciences, Physical Sciences, and Technology.

In parallel, our research addresses important issues around law, ethics and economics, in order to apply data science to solve challenging problems for society.

C2D3 supports collaboration and knowledge transfer in this growing field.

Join us.