Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Maslovskaya, Sofya"'
The depth of networks plays a crucial role in the effectiveness of deep learning. However, the memory requirement for backpropagation scales linearly with the number of layers, which leads to memory bottlenecks during training. Moreover, deep network
Externí odkaz:
http://arxiv.org/abs/2410.09537
Differential equations posed on quadratic matrix Lie groups arise in the context of classical mechanics and quantum dynamical systems. Lie group numerical integrators preserve the constants of motions defining the Lie group. Thus, they respect import
Externí odkaz:
http://arxiv.org/abs/2408.13043
Motivated by mechanical systems with symmetries, we focus on optimal control problems possessing symmetries. Following recent works, which generalized the classical concept of static turnpike to manifold turnpike, we extend the exponential turnpike p
Externí odkaz:
http://arxiv.org/abs/2406.14286
Autor:
Jean, Frédéric, Maslovskaya, Sofya
Inverse optimal control problem emerges in different practical applications, where the goal is to design a cost function in order to approximate given optimal strategies of an expert. Typical application is in robotics for generation of human motions
Externí odkaz:
http://arxiv.org/abs/2406.14270
Autor:
Maslovskaya, Sofya, Ober-Blöbaum, Sina
Deep learning is widely used in tasks including image recognition and generation, in learning dynamical systems from data and many more. It is important to construct learning architectures with theoretical guarantees to permit safety in the applicati
Externí odkaz:
http://arxiv.org/abs/2406.04104
Autor:
Leyendecker, Sigrid, Maslovskaya, Sofya, Ober-Blobaum, Sina, de Almagro, Rodrigo T. Sato Martin, Szemenyei, Flora Orsolya
In this work, we consider optimal control problems for mechanical systems on vector spaces with fixed initial and free final state and a quadratic Lagrange term. Specifically, the dynamics is described by a second order ODE containing an affine contr
Externí odkaz:
http://arxiv.org/abs/2307.13402
H. Weyl in 1921 demonstrated that for a connected manifold of dimension greater than $1$, if two Riemannian metrics are conformal and have the same geodesics up to a reparametrization, then one metric is a constant scaling of the other one. In the pr
Externí odkaz:
http://arxiv.org/abs/2001.08584
Autor:
Maslovskaya, Sofya
Cette thèse s'insère dans un projet plus vaste, dont le but est de s'attaquer aux fondements mathématiques du problème inverse en contrôle optimal afin de dégager une méthodologie générale utilisable en neurophysiologie. Les deux questions e
Externí odkaz:
http://www.theses.fr/2018SACLY013/document
Publikováno v:
In IFAC PapersOnLine July 2017 50(1):500-505
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.