Research

I study representation learning for dynamical systems with applications to the life sciences, from the genetic to the behavioral levels.
Some major currents include the unsupervised inference of governing
equations and bifurcation prediction in cell cycle dynamics. Other recent
work has explored machine learning methods for optimal control, particularly of
systems of coupled oscillators, which we have used to model the
cortical processes
underlying higher visual cognition. Here is an overview of ongoing and former work:

for dynamical systems

- Ricci, M.G., Moriel, M., Piran, Z., and Nitzan, M. Phase2vec: Dynamical system embedding with a physics-informed convolutional network. ICLR 2023 (Spotlight)
- Ricci, Moriel, M., Ricci, M.G., Nitzan, M. Let's do the time-warp-attend: Learning topologically-invariant representations of dynamical systems (Submitted)

structure of biological PDEs

- Ricci, M.G., Moriel, N., Nitzan, M. Spatial Phase2vec: Learning a PDE embedding space with applications to reaction-diffusion models (In preparation)

- Ricci, M.G., Thackray, J., Tischfield, M., Abraira, V. Animal2Vec: Dynamical embedding methods for computational ethology (In preparation)
- Bohic, M., Pattison, L.A., Jhumka, Z.A., Rossi, H., Thackray, J.K., Ricci, M.G., Foster, W., Arnold, J., Mossazghi, N., Yttri, E.A.,Tischfield, M.A., Smith, E. S-J, Abdus-Saboor, I., Abraira, V. (2021) Mapping the neuroethological signatures of pain, analgesia and recovery in mice. Neuron, 2023
- Theis, T., Thackray, J.K., Ricci, M.G., Abraira, V. A machine vision approach for automated locomotor recovery at millisecond timescales. 38th Annual National Neurotrauma Symposium, Virtual. July 11-14, 2021.

adaptive network dynamics

how to connect them to achieve an optimal dynamics? [Github]

- Ricci, M.G., Jung, M., Zhang, Y., Chalvidal, M., Soni, A.,& Serre, T. KuraNet: Systems of Coupled Oscillators that Learn to Synchronize
- Chalvidal, M., Ricci, M.G., Serre, T., VanRullen, R. (2021) Go With the Flow: Adaptive Control for Neural ODEs. ICLR 2021
- Ricci, M.G., Zhang, Y., Soni, A., Jung, M., & Serre, T. Kura-Net: Exploring systems of coupled oscillators using deep learning. COSYNE, 2020.
- Ricci, M.G., Windolf, C., & M., Serre, T., A Formal Model of Neural Synchrony for Unsupervised Image Grouping. COSYNE, 2019.

of visual reasoning

principles of neural dynamics underlie this ability?

- Alamia, A., Luo, C., Ricci, M.G., Kim, J., Serre, T., VanRullen, R. Differential involvement of EEG oscillatory components in sameness vs. spatial-relation visual reasoning tasks. bioRxiv 2019.12.16.877829
- Ricci, M., Cadène, R., & Serre, T. (2020). Same-different conceptualization : A machine vision perspective. Current Opinion in Behavioral Sciences, 37, 47–55. https://doi.org/10.1016/j.cobeha.2020.08.008
- Kim, J., Ricci, M.G., & Serre, T. (2018). Not-So-CLEVR : learning same – different relations strains feedforward neural networks. Royal Society Interface, 8(2018011)
- Ricci, M.G., Kim, J., & Serre, T. (2018). Same-different problems strain convolutional neural networks. In Proceedings of the 40th Annual Cognitive Science Society. Madison, WI: Cognitive Science Society. [cs.LG]