Integrated circuit with memristor emulator array and neuron circuits for neuromorphic pattern recognition

Rajeev Ranjan, Alexandros Kyrmanidis, Wolf Lukas Hellweg, Pablo Mendoza Ponce, Lait Abu Saleh, Dietmar Schroeder, Wolfgang H. Krautschneider

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

4 Citas (Scopus)

Resumen

This paper details an array of switch resistor based memristor emulators with integrate & fire based neuron ASIC for the development of memristor based pattern recognition. The designed ASIC has 4 memristor emulators with a conductance range from 195 nS to 190 uS; processing has been planned to be off-chip to get the freedom of programmability of any function in ASIC. The ASIC has 2 integrate and fire (I & F) neuron circuits which are planned to be used in conjunction with memristors in a large multiple chip network for pattern recognition. This paper explains the memristor emulator, I & F neurons and an algorithm of pattern recognition simulated in Ltspice. The ASIC has been fabricated in AMS 350nm process.

Idioma originalInglés
Título de la publicación alojada2016 39th International Conference on Telecommunications and Signal Processing, TSP 2016
EditoresNorbert Herencsar
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas265-268
Número de páginas4
ISBN (versión digital)9781509012886
DOI
EstadoPublicada - 28 nov 2016
Publicado de forma externa
Evento39th International Conference on Telecommunications and Signal Processing, TSP 2016 - Vienna, Austria
Duración: 27 jun 201629 jun 2016

Serie de la publicación

Nombre2016 39th International Conference on Telecommunications and Signal Processing, TSP 2016

Conferencia

Conferencia39th International Conference on Telecommunications and Signal Processing, TSP 2016
País/TerritorioAustria
CiudadVienna
Período27/06/1629/06/16

Huella

Profundice en los temas de investigación de 'Integrated circuit with memristor emulator array and neuron circuits for neuromorphic pattern recognition'. En conjunto forman una huella única.

Citar esto