On Information Processing with Networks of Nano-Scale Switching Elements
Journal article, 2014

Unconventional computing explores multi-scale platforms connecting molecular-scale devices into networks for the development of scalable neuromorphic architectures, often based on new materials and components with new functionalities. We review some work investigating the functionalities of locally connected networks of different types of switching elements as computational substrates. In particular, we discuss reservoir computing with networks of nonlinear nanoscale components. In usual neuromorphic paradigms, the network synaptic weights are adjusted as a result of a training/learning process. In reservoir computing, the non-linear network acts as a dynamical system mixing and spreading the input signals over a large state space, and only a readout layer is trained. We illustrate the most important concepts with a few examples, featuring memristor networks with time-dependent and history dependent resistances.

MOLECULAR ELECTRONICS

LIQUID-STATE MACHINE

SYSTEMS

LOGIC GATES

molecular network

MEMRISTIVE DEVICES

MEMORY

Reservoir computing

RECURRENT NEURAL-NETWORKS

JUNCTIONS

CONNECTIVITY

COMPUTATION

memristor

dynamic system

Author

Zoran Konkoli

Chalmers, Applied Physics, Electronics Material and Systems

Göran Wendin

Chalmers, Applied Physics, Electronics Material and Systems

International Journal of Unconventional Computing

1548-7199 (ISSN) 1548-7202 (eISSN)

Vol. 10 5-6 405-428

SYnaptic MOlecular NEtworks for Bio-inspired Information Processing (SYMONE)

European Commission (EC) (EC/FP7/318597), 2012-09-01 -- 2015-08-31.

Subject Categories

Computer and Information Science

More information

Latest update

8/8/2023 6