Synergizing physics and machine learning for advanced battery management.

Improving battery health and safety motivates the synergy of a powerful duo: physics and machine learning. Through seamless integration of these disciplines, the efficacy of mathematical battery models can be significantly enhanced. This paper delves into the challenges and potentials of managing battery health and safety, highlighting the transformative impact of integrating physics and machine learning to address those challenges.

Economic and environmental benefits of automated electric vehicle ride-hailing services in New York City.

A precise, scalable, and computationally efficient mathematical framework is proposed for region-wide autonomous electric vehicle (AEV) fleet management, sizing and infrastructure planning for urban ride-hailing services. A comprehensive techno-economic analysis in New York City is conducted not only to calculate the societal costs but also to quantify the environmental and health benefits resulting from reduced emissions. The results reveal that strategic fleet management can reduce fleet size and unnecessary cruising mileage by up to 40% and 70%, respectively.

Hopfield Neural Network Flow: A Geometric Viewpoint.

We provide gradient flow interpretations for the continuous-time continuous-state Hopfield neural network (HNN). The ordinary and stochastic differential equations associated with the HNN were introduced in the literature as analog optimizers and were reported to exhibit good performance in numerical experiments. In this work, we point out that the deterministic HNN can be transcribed into Amari's natural gradient descent, and thereby uncover the explicit relation between the underlying Riemannian metric and the activation functions.