Optimized pulsed write schemes improve linearity and write speed for low-power organic neuromorphic devices

Scott T. Keene, Armantas Melianas, Elliot J. Fuller, Yoeri van de Burgt, A. Alec Talin, Alberto Salleo

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

26 Citaten (Scopus)
7 Downloads (Pure)

Samenvatting

Neuromorphic devices are becoming increasingly appealing as efficient emulators of neural networks used to model real world problems. However, no hardware to date has demonstrated the necessary high accuracy and energy efficiency gain over CMOS in both (1) training via backpropagation and (2) in read via vector matrix multiplication. Such shortcomings are due to device non-idealities, particularly asymmetric conductance tuning in response to uniform voltage pulse inputs. Here, by formulating a general circuit model for capacitive ion-exchange neuromorphic devices, we show that asymmetric nonlinearity in organic electrochemical neuromorphic devices (ENODes) can be suppressed by an appropriately chosen write scheme. Simulations based upon our model suggest that a nonlinear write-selector could reduce the switching voltage and energy, enabling analog tuning via a continuous set of resistance states (100 states) with extremely low switching energy (∼170 fJ • μm-2). This work clarifies the pathway to neural algorithm accelerators capable of parallelism during both read and write operations.

Originele taal-2Engels
Artikelnummer224002
Aantal pagina's8
TijdschriftJournal of Physics D: Applied Physics
Volume51
Nummer van het tijdschrift22
DOI's
StatusGepubliceerd - 6 jun 2018

Vingerafdruk

Duik in de onderzoeksthema's van 'Optimized pulsed write schemes improve linearity and write speed for low-power organic neuromorphic devices'. Samen vormen ze een unieke vingerafdruk.

Citeer dit