Reservoir computing with networks of nanoscale memristors: optimisation of memristor responses for maximal computational performance
- 22 August 2025
- journal article
- research article
- Published by Royal Society of Chemistry (RSC) in Nanoscale
- Vol. 17 (37) , 21481-21493
Abstract
Self-assembled networks of memristors can successfully perform various computational tasks. Here we demonstate the effect of tuning memristor parameters on computational performance.Keywords
Funding Information
- MacDiarmid Institute for Advanced Materials and Nanotechnology
- Marsden Fund
This publication has 40 references indexed in Scilit:
- Self‐organized Criticality in Neuromorphic Nanowire Networks With Tunable and Local DynamicsAdvanced Functional Materials, 2025
- Experimental Demonstration of Reservoir Computing with Self‐Assembled Percolating Networks of NanoparticlesAdvanced Materials, 2024
- Reservoir computing with 3D nanowire networksNeural Networks, 2022
- Emergence of In‐Materio Intelligence from an Incidental Structure of a Single‐Walled Carbon Nanotube–Porphyrin Polyoxometalate Random NetworkAdvanced Intelligent Systems, 2022
- Stochastic Spiking Behavior in Neuromorphic Networks Enables True Random Number GenerationACS Applied Materials & Interfaces, 2021
- 1/f Noise and Machine Intelligence in a Nonlinear Dopant Atom NetworkSmall Science, 2021
- Atomic Scale Dynamics Drive Brain-like Avalanches in Percolating Nanostructured NetworksNano Letters, 2020
- Recent advances in physical reservoir computing: A reviewNeural Networks, 2019
- Emergent Criticality in Complex Turing B‐Type Atomic Switch NetworksAdvanced Materials, 2011
- Reservoir computing approaches to recurrent neural network trainingComputer Science Review, 2009