Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Portegies, Jim"'
Publikováno v:
LIPIcs, Volume 303, TYPES 2023
Using the language of homotopy type theory (HoTT), we 1) prove a synthetic version of the classification theorem for covering spaces, and 2) explore the existence of canonical change-of-basepoint isomorphisms between homotopy groups. There is some fr
Externí odkaz:
http://arxiv.org/abs/2409.15351
We introduce a class of trainable nonlinear operators based on semirings that are suitable for use in neural networks. These operators generalize the traditional alternation of linear operators with activation functions in neural networks. Semirings
Externí odkaz:
http://arxiv.org/abs/2405.18805
Autor:
Wemmenhove, Jelle, Arends, Dick, Beurskens, Thijs, Bhaid, Maitreyee, McCarren, Sean, Moraal, Jan, Garrido, Diego Rivera, Tuin, David, Vassallo, Malcolm, Wils, Pieter, Portegies, Jim
Publikováno v:
EPTCS 400, 2024, pp. 96-119
In order to help students learn how to write mathematical proofs, we adapt the Coq proof assistant into an educational tool we call Waterproof. Like with other interactive theorem provers, students write out their proofs inside the software using a s
Externí odkaz:
http://arxiv.org/abs/2211.13513
Advanced feedforward control methods enable mechatronic systems to perform varying motion tasks with extreme accuracy and throughput. The aim of this paper is to develop a data-driven feedforward controller that addresses input nonlinearities, which
Externí odkaz:
http://arxiv.org/abs/2209.11504
In pursuit of enhanced multi-agent collaboration, we analyze several on-policy deep reinforcement learning algorithms in the recently published Hanabi benchmark. Our research suggests a perhaps counter-intuitive finding, where Proximal Policy Optimiz
Externí odkaz:
http://arxiv.org/abs/2203.11656
Mechatronic systems have increasingly high performance requirements for motion control. The low-frequency contribution of the flexible dynamics, i.e. the compliance, should be compensated for by means of snap feedforward to achieve high accuracy. Pos
Externí odkaz:
http://arxiv.org/abs/2202.00257
Mechatronic systems have increasingly stringent performance requirements for motion control, leading to a situation where many factors, such as position-dependency, cannot be neglected in feedforward control. The aim of this paper is to compensate fo
Externí odkaz:
http://arxiv.org/abs/2201.07511
Feedforward control is essential to achieving good tracking performance in positioning systems. The aim of this paper is to develop an identification strategy for inverse models of systems with nonlinear dynamics of unknown structure using input-outp
Externí odkaz:
http://arxiv.org/abs/2112.03805
Learning from data of past tasks can substantially improve the accuracy of mechatronic systems. Often, for fast and safe learning a model of the system is required. The aim of this paper is to develop a model-free approach for fast and safe learning
Externí odkaz:
http://arxiv.org/abs/2007.00430
We present a PDE-based framework that generalizes Group equivariant Convolutional Neural Networks (G-CNNs). In this framework, a network layer is seen as a set of PDE-solvers where geometrically meaningful PDE-coefficients become the layer's trainabl
Externí odkaz:
http://arxiv.org/abs/2001.09046