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...
Главные авторы: | Tayfun Gokmen, Murat Onen, Wilfried Haensch |
---|---|
Формат: | Статья |
Язык: | English |
Опубликовано: |
Frontiers Media S.A.
2017-10-01
|
Серии: | Frontiers in Neuroscience |
Предметы: | |
Online-ссылка: | http://journal.frontiersin.org/article/10.3389/fnins.2017.00538/full |
Схожие документы
-
Training LSTM Networks With Resistive Cross-Point Devices
по: Tayfun Gokmen, и др.
Опубликовано: (2018-10-01) -
MR-PIPA: An Integrated Multilevel RRAM (HfO<sub><italic>x</italic></sub>)-Based Processing-In-Pixel Accelerator
по: Minhaz Abedin, и др.
Опубликовано: (2022-01-01) -
Reliable and Energy-Efficient Diabetic Retinopathy Screening Using Memristor-Based Neural Networks
по: Sumit Diware, и др.
Опубликовано: (2024-01-01) -
Design implementations of ternary logic systems: A critical review
по: Furqan Zahoor, и др.
Опубликовано: (2024-09-01) -
Accurate Inference With Inaccurate RRAM Devices: A Joint Algorithm-Design Solution
по: Gouranga Charan, и др.
Опубликовано: (2020-01-01)