Neuromorphic hardware for somatosensory neuroprostheses
In individuals with sensory-motor impairments, missing limb functions can be restored using
neuroprosthetic devices that directly interface with the nervous system. However, restoring …
neuroprosthetic devices that directly interface with the nervous system. However, restoring …
Learning from the past: reservoir computing using delayed variables
U Parlitz - Frontiers in Applied Mathematics and Statistics, 2024 - frontiersin.org
Reservoir computing is a machine learning method that is closely linked to dynamical
systems theory. This connection is highlighted in a brief introduction to the general concept …
systems theory. This connection is highlighted in a brief introduction to the general concept …
[HTML][HTML] A perspective on physical reservoir computing with nanomagnetic devices
Neural networks have revolutionized the area of artificial intelligence and introduced
transformative applications to almost every scientific field and industry. However, this …
transformative applications to almost every scientific field and industry. However, this …
Neuromorphic overparameterisation and few-shot learning in multilayer physical neural networks
Physical neuromorphic computing, exploiting the complex dynamics of physical systems,
has seen rapid advancements in sophistication and performance. Physical reservoir …
has seen rapid advancements in sophistication and performance. Physical reservoir …
Reservoir computing with delayed input for fast and easy optimisation
Reservoir computing is a machine learning method that solves tasks using the response of a
dynamical system to a certain input. As the training scheme only involves optimising the …
dynamical system to a certain input. As the training scheme only involves optimising the …
Reservoir computing with diverse timescales for prediction of multiscale dynamics
Machine learning approaches have recently been leveraged as a substitute or an aid for
physical/mathematical modeling approaches to dynamical systems. To develop an efficient …
physical/mathematical modeling approaches to dynamical systems. To develop an efficient …
[HTML][HTML] Voltage-controlled superparamagnetic ensembles for low-power reservoir computing
We propose thermally driven, voltage-controlled superparamagnetic ensembles as low-
energy platforms for hardware-based reservoir computing. In the proposed devices, thermal …
energy platforms for hardware-based reservoir computing. In the proposed devices, thermal …
[PDF][PDF] Adaptive programmable networks for in materia neuromorphic computing
Modern AI and machine-learning provide striking performance. However, this comes with
rapidly-spiralling energy costs 1, 2 arising from growing network size and inefficiencies of …
rapidly-spiralling energy costs 1, 2 arising from growing network size and inefficiencies of …
Reservoir computing for temporal data classification using a dynamic solid electrolyte ZnO thin film transistor
The processing of sequential and temporal data is essential to computer vision and speech
recognition, two of the most common applications of artificial intelligence (AI). Reservoir …
recognition, two of the most common applications of artificial intelligence (AI). Reservoir …
An inkjet-printed artificial neuron for physical reservoir computing
SD Gardner, MR Haider - IEEE Journal on Flexible Electronics, 2022 - ieeexplore.ieee.org
Inkjet printing circuits onto thin, flexible substrates is a newly explored field with respect to
the transistor; a critical element needed to form logic gates and high-level active circuitry …
the transistor; a critical element needed to form logic gates and high-level active circuitry …