November 28, 2025 — 11:00 ABSTRACT : Surprisingly, many optimisation phenomena observed in complex neural networks also appear in so-called 2-layer diagonal linear networks. This rudimentary architecture—a two-layer feedforward linear network with a diagonal inner weight matrix—has the advantage of revealing key training characteristics while keeping the theoretical analysis clean and insightful. In this talk, […]
Thursday 27th November 2025 at 2pm, in Salle Hooper, 3rd floor at IBM building, 14 Rue Jean Rostand, 91400 Orsay Salle Hooper,3rd floor at IBM building,14 Rue Jean Rostand, 91400 Orsay Speakers: Alfeu J. Sguarezi Filho (Federal University of ABC, Brasil) Title: Predictive Control Strategies for Electric Traction, Wind Energy, and Smart Grid Applications Abstract: This presentation aims […]
November 21, 2025 — 14:00 Abstract This work proposes a Bayesian rule based on the mixture of a point mass function at zero and the logistic distribution to perform wavelet shrinkage in nonparametric regression models with stationary errors (with short or longmemory behavior). The proposal is assessed through Monte Carlo experiments and illustrated with real […]
The ninetieth UQSay seminar on UQ, DACE and related topics will take place online on Thursday afternoon, November 20, 2025. 2–3 PM — Fanny Lehmann (ETH AI Center, ETH Zurich) Foundation Models of the Earth System: Seeing Beyond Weather Deep learning has revolutionized weather forecasting over the past three years, with AI models surpassing the […]
November 07, 2025 — 11:00 — Online Abstract The empirical wavelet transform (EWT) is a data-driven time-scale representation based on adaptive filters. Its robustness and flexibility have led to significant developments and a growing number of applications over the past decade. However, most studies have focused on theoretical aspects for one-dimensional signals, and extensions to […]
