
Dr Rui Ponte Costa
BEng, MSc, MRes, PhD
Expertise
I develop unifying theories of learning in the brain that are inspired by machine learning algorithms.
Current positions
Senior Research Fellow
School of Engineering Mathematics and Technology
Contact
Press and media
Many of our academics speak to the media as experts in their field of research. If you are a journalist, please contact the University’s Media and PR Team:
Biography
I did my PhD at the University of Edinburgh (UK) as part of the Institute for Adaptive and Neural Computation where I established a collaboration between theoretical (Mark van Rossum) and experimental groups (P. Jesper Sjöström). I was also a visiting PhD student at University College London (UK) and McGill University (Canada). After that, I conducted postdoctoral research in computational neuroscience & machine learning at the University of Oxford (UK) with Tim Vogels where I established collaborations with the groups of Nando de Freitas (Oxford/Google Deepmind) and Nigel Emptage (Oxford). During my time at Oxford I co-organised the Oxford NeuroTheory Forum. Next, I did a short postdoc with the group of Walter Senn (Bern, Switzerland) in collaboration with Yoshua Bengio (MILA). In 2018 I moved to the University of Bristol to start my own group (Neural & Machine Learning group).
Research interests
I lead the Neural and Machine learning group. Our group seeks to understand the principles underlying learning in the brain. To this end, we bring neural and machine learning together across multiple levels. We collaborate with experimental and theoretical neuroscience, and machine learning groups in the UK and internationally.
We are part of the Bristol Computational Neuroscience Unit, Faculty of Engineering and interact closely with the Bristol Neuroscience and machine learning communities.
Projects and supervisions
Research projects
AI-driven modelling for cortex-wide neuromodulated learning
Principal Investigator
Managing organisational unit
Department of Computer ScienceDates
15/02/2023 to 14/12/2024
AI-driven modelling for cortex-wide neuromodulated learning
Principal Investigator
Managing organisational unit
Department of Computer ScienceDates
15/02/2023 to 14/12/2024
AI-driven modelling for cortex-wide neuromodulated learning
Principal Investigator
Managing organisational unit
School of Engineering Mathematics and TechnologyDates
15/02/2023 to 14/12/2024
AI-driven brain modelling for neuromodulated cognitive enhancement
Principal Investigator
Managing organisational unit
Department of Computer ScienceDates
01/09/2022 to 28/02/2023
AI-driven brain modelling for neuromodulated cognitive enhancement
Principal Investigator
Managing organisational unit
Department of Computer ScienceDates
01/09/2022 to 28/02/2023
Thesis supervisions
Publications
Selected publications
04/01/2023Cerebro-cerebellar networks facilitate learning through feedback decoupling
Nature Communications
Single-phase deep learning in cortico-cortical networks
Neural Information Processing Systems (NeurIPS 2022)
Developmental depression-to-facilitation shift controls excitation-inhibition balance
Communications Biology
Cortico-cerebellar networks as decoupling neural interfaces
Neural Information Processing Systems 35 (NeurIPS 2021)
A deep learning framework for neuroscience
Nature Neuroscience
Recent publications
04/01/2023Cerebro-cerebellar networks facilitate learning through feedback decoupling
Nature Communications
Lost in Latent Space: Examining failures of disentangled models at combinatorial generalisation
Advances in Neural Information Processing Systems
Single-phase deep learning in cortico-cortical networks
Neural Information Processing Systems (NeurIPS 2022)
Cerebellar-driven cortical dynamics enable task acquisition, switching and consolidation
Distributional coding of associative learning within projection-defined populations of midbrain dopamine neurons
Teaching
Currently involved in three units: Machine Learning, Information Processing in the Brain and Math for Computer Scientists A.