activity
20142023
most citedControlling Recurrent Neural Networks by Conceptors

92 citations · 208 across the 9 of their papers we have counts for

collaborators

9 papers

cs.ET2023★ 1 cited

Toward a formal theory for computing machines made out of whatever physics offers: extended version

Herbert Jaeger, Beatriz Noheda, Wilfred G. van der Wiel

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 s…

cs.ET2023★ 2 cited

Timescales: the choreography of classical and unconventional computing

Herbert Jaeger, Francky Catthoor

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 s…

cs.ET2021★ 9 cited

Dimensions of Timescales in Neuromorphic Computing Systems

Herbert Jaeger, Dirk Doorakkers, Celestine Lawrence +1

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 I…

cs.ET2020★ 69 cited

Exploring the landscapes of "computing": digital, neuromorphic, unconventional -- and beyond

Herbert Jaeger

The acceleration race of digital computing technologies seems to be steering toward impasses -- technological, economical and environmental -- a condition that has spurred research…

cs.CC2018★ 10 cited

Computing optimal discrete readout weights in reservoir computing is NP-hard

Fatemeh Hadaeghi, Herbert Jaeger

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 r…

cs.NE2017★ 10 cited

Overcoming Catastrophic Interference by Conceptors

Xu He, Herbert Jaeger

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"…