Clémentine Dominé

I am a Ph.D. candidate at the Gatsby Computational Neuroscience Unit, supervised by Andrew Saxe and Caswell Barry, working at the intersection of theoretical neuroscience and theoretical machine learning. My research seeks to develop mathematical toolkits suitable for describing complex and flexible learning mechanisms in both artificial and biological agents.

I focus on continual learning, reversal learning, and the acquisition of structured knowledge. Specifically, I study the theory of deep learning, which involves artificial neural networks inspired by the brain. By integrating deep learning theory, engineering, and insights from biological intelligence, I aim to enhance the ability of deep learning systems to continuously learn, adapt, and revise their knowledge in response to new users and contexts.

*First Author

Published

• Dominé, C. *, Braun, L., Fitzgerald, J.E., and Saxe, A.M., 2023. Exact learning dynamics of deep linear networks with prior knowledge. *Journal of Statistical Mechanics: Theory and Experiment, 2023(11), p.114004.
• Braun, L.*, Dominé, C.*, Fitzgerald, J., and Saxe, A., 2022. Exact learning dynamics of deep linear networks with prior knowledge. Advances in Neural Information Processing Systems, 35, pp.6615-6629.
• Pegoraro, M. *, Dominé, C. *, Rodolà, E., Veličković, P., and Deac, A., 2023. Geometric Epitope and Paratope Prediction. bioRxiv, pp.2023-06. (Accepted in Bioinformatics)

Pre-Print/Under-Review

• Kunin, D., Raventós, A., Dominé, C., Chen, F., Klindt, D., Saxe, A. & Ganguli, S., 2024. Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning. arXiv preprint, 2406.06158.
• Thompson, E., Rollik, L., Waked, B., Mills, G., Kaur, J., Geva, B., Carrasco-Davis, R., George, T., Domine, C., Dorrell, W. and Stephenson-Jones, M., 2024. Replay of procedural experience is independent of the hippocampus. bioRxiv, pp.2024-06.
• Dominé, C. *, Carrasco Davis, R.A. *, Hollingsworth, L., Sirmpilatze, N., Tyson, A.L., Jarvis, D., Barry, C., and Saxe, A.M., 2024. Neural Playground: A Standardised Environment for Evaluating Models of Hippocampus and Entorhinal Cortex. bioRxiv, pp.2024-03.