2 papers
cs.CV2022
Learning with Signatures
J. de Curtò, I. de Zarzà, Hong Yan +1
In this work we investigate the use of the Signature Transform in the context of Learning. Under this assumption, we advance a supervised framework that potentially provides state-…
cs.LG2019
Doctor of Crosswise: Reducing Over-parametrization in Neural Networks
J. D. Curtó, I. C. Zarza, Kris Kitani +2
Dr. of Crosswise proposes a new architecture to reduce over-parametrization in Neural Networks. It introduces an operand for rapid computation in the framework of Deep Learning tha…