[PDF][PDF] Sample-level sound synthesis with recurrent neural networks and conceptors

C Kiefer - PeerJ Computer Science, 2019 - peerj.com
Conceptors are a recent development in the field of reservoir computing; they can be used to
influence the dynamics of recurrent neural networks (RNNs), enabling generation of …

Controlling Recurrent Neural Networks by Diagonal Conceptors

JP De Jong - arXiv preprint arXiv:2107.07968, 2021 - arxiv.org
The human brain is capable of learning, memorizing, and regenerating a panoply of
temporal patterns. A neuro-dynamical mechanism called conceptors offers a method for …

Transfer between long-term and short-term memory using Conceptors

A Strock, N Rougier, X Hinaut - arXiv preprint arXiv:2003.11640, 2020 - arxiv.org
We introduce a recurrent neural network model of working memory combining short-term
and long-term components. e short-term component is modelled using a gated reservoir …

Working memory in random recurrent neural networks

A Strock - 2020 - theses.hal.science
Working memory can be defined as the ability to temporarily store and manipulate
information of any kind. For example, imagine that you are asked to mentally add a series of …

Latent space exploration and functionalization of a gated working memory model using conceptors

A Strock, NP Rougier, X Hinaut - Cognitive Computation, 2023 - Springer
Working memory is the ability to maintain and manipulate information. We introduce a
method based on conceptors that allows us to manipulate information stored in the …

[PDF][PDF] Analyse von Smartphone-Sensordaten mit rekurrenten neuronalen Netzen zur Klassifikation von Fahrmanövern

O Otto - 2020 - repo.bibliothek.uni-halle.de
Dieses Kapitel vermittelt die grundlegende Motivation, einen Ansatz zu untersuchen, mit
dem Fahrerassistenzsysteme zur Unfallvermeidung realisiert werden könnten. Die Relevanz …