Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices

Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices

In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN) in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU) devices to convolutional n...

Cijeli opis

Bibliografski detalji
Glavni autori: Tayfun Gokmen, Murat Onen, Wilfried Haensch
Format: Članak
Jezik:English
Izdano: Frontiers Media S.A. 2017-10-01
Serija:Frontiers in Neuroscience
Teme:
convolutional neural networks (CNN)
resistive processing unit (RPU)
deep neural network
deep learning
resistive switching
resistive random access memory (RRAM)
Online pristup:http://journal.frontiersin.org/article/10.3389/fnins.2017.00538/full

Internet

http://journal.frontiersin.org/article/10.3389/fnins.2017.00538/full

Slični predmeti