Tommaso Salvatori
Biography
I did my Bsc Theoretical Mathematics at La Sapienza University in Rome, focusing mainly on Geometry and Topology. My bachelor dissertation was on the Poincaré-Hopf theorem in Differential Geometry. I graduated from a MSc in Mathematics in January 2018, again from La Sapienza University with a thesis on Chromatic Homotopy Theory written in Berlin and supervised by Shane Kelly.
Selected Publications
-
Mathematical Capabilities of ChatGPT
Simon Frieder‚ Luca Pinchetti‚ Alexis Chevalier‚ Ryan−Rhys Griffiths‚ Tommaso Salvatori‚ Thomas Lukasiewicz‚ Philipp Christian Petersen and Julius Berner
In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 3‚ NeurIPS Datasets and Benchmarks 2023‚ December 2023. December, 2023.
Details about Mathematical Capabilities of ChatGPT | BibTeX data for Mathematical Capabilities of ChatGPT
-
Associative Memories in the Feature Space
Tommaso Salvatori‚ Beren Millidge‚ Yuhang Song‚ Rafal Bogacz and Thomas Lukasiewicz
In Proceedings of the 26th European Conference on Artificial Intelligence‚ ECAI 2023‚ Kraków‚ Poland‚ September 30 – October 5‚ 2023. IOS Press. September, 2023.
Details about Associative Memories in the Feature Space | BibTeX data for Associative Memories in the Feature Space
-
Backpropagation at the Infinitesimal Inference Limit of Energy−Based Models: Unifying Predictive Coding‚ Equilibrium Propagation‚ and Contrastive Hebbian Learning
Beren Millidge‚ Yuhang Song‚ Tommaso Salvatori‚ Thomas Lukasiewicz and Rafal Bogacz
In Proceedings of the 11th International Conference on Learning Representations‚ ICLR 2023‚ Kigali‚ Rwanda‚ 1–5 May 2023. OpenReview.net. May, 2023.
Details about Backpropagation at the Infinitesimal Inference Limit of Energy−Based Models: Unifying Predictive Coding‚ Equilibrium Propagation‚ and Contrastive Hebbian Learning | BibTeX data for Backpropagation at the Infinitesimal Inference Limit of Energy−Based Models: Unifying Predictive Coding‚ Equilibrium Propagation‚ and Contrastive Hebbian Learning | Link to Backpropagation at the Infinitesimal Inference Limit of Energy−Based Models: Unifying Predictive Coding‚ Equilibrium Propagation‚ and Contrastive Hebbian Learning