Zobrazeno 1 - 10
of 160
pro vyhledávání: '"Jaeger, Herbert"'
Approaching limitations of digital computing technologies have spurred research in neuromorphic and other unconventional approaches to computing. Here we argue that if we want to systematically engineer computing systems that are based on unconventio
Externí odkaz:
http://arxiv.org/abs/2307.15408
Autor:
Jaeger, Herbert, Catthoor, Francky
Tasks that one wishes to have done by a computer often come with conditions that relate to timescales. For instance, the processing must terminate within a given time limit; or a signal processing computer must integrate input information across seve
Externí odkaz:
http://arxiv.org/abs/2301.00893
This article is a public deliverable of the EU project "Memory technologies with multi-scale time constants for neuromorphic architectures" (MeMScales, https://memscales.eu, Call ICT-06-2019 Unconventional Nanoelectronics, project number 871371). Thi
Externí odkaz:
http://arxiv.org/abs/2102.10648
Autor:
Jaeger, Herbert
The acceleration race of digital computing technologies seems to be steering toward impasses -- technological, economical and environmental -- a condition that has spurred research efforts in alternative, "neuromorphic" (brain-like) computing technol
Externí odkaz:
http://arxiv.org/abs/2011.12013
Autor:
Hadaeghi, Fatemeh, Jaeger, Herbert
Publikováno v:
Neurocomputing Volume 338, 21 April 2019, Pages 233-236
We show NP-hardness of a generalized quadratic programming problem, which we called Unconstrained N-ary Quadratic Programming (UNQP). This problem has recently become practically relevant in the context of novel memristor-based neuromorphic microchip
Externí odkaz:
http://arxiv.org/abs/1809.01021
Autor:
He, Xu, Jaeger, Herbert
Catastrophic interference has been a major roadblock in the research of continual learning. Here we propose a variant of the back-propagation algorithm, "conceptor-aided back-prop" (CAB), in which gradients are shielded by conceptors against degradat
Externí odkaz:
http://arxiv.org/abs/1707.04853
Autor:
Jaeger, Herbert
Conceptors provide an elementary neuro-computational mechanism which sheds a fresh and unifying light on a diversity of cognitive phenomena. A number of demanding learning and processing tasks can be solved with unprecedented ease, robustness and acc
Externí odkaz:
http://arxiv.org/abs/1406.2671
Autor:
Jaeger, Herbert
The human brain is a dynamical system whose extremely complex sensor-driven neural processes give rise to conceptual, logical cognition. Understanding the interplay between nonlinear neural dynamics and concept-level cognition remains a major scienti
Externí odkaz:
http://arxiv.org/abs/1403.3369
A method is provided for designing and training noise-driven recurrent neural networks as models of stochastic processes. The method unifies and generalizes two known separate modeling approaches, Echo State Networks (ESN) and Linear Inverse Modeling
Externí odkaz:
http://arxiv.org/abs/1402.1613
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.