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...
Hoofdauteurs: | Tayfun Gokmen, Murat Onen, Wilfried Haensch |
---|---|
Formaat: | Artikel |
Taal: | English |
Gepubliceerd in: |
Frontiers Media S.A.
2017-10-01
|
Reeks: | Frontiers in Neuroscience |
Onderwerpen: | |
Online toegang: | http://journal.frontiersin.org/article/10.3389/fnins.2017.00538/full |
Gelijkaardige items
-
Training LSTM Networks With Resistive Cross-Point Devices
door: Tayfun Gokmen, et al.
Gepubliceerd in: (2018-10-01) -
MR-PIPA: An Integrated Multilevel RRAM (HfO<sub><italic>x</italic></sub>)-Based Processing-In-Pixel Accelerator
door: Minhaz Abedin, et al.
Gepubliceerd in: (2022-01-01) -
Reliable and Energy-Efficient Diabetic Retinopathy Screening Using Memristor-Based Neural Networks
door: Sumit Diware, et al.
Gepubliceerd in: (2024-01-01) -
Design implementations of ternary logic systems: A critical review
door: Furqan Zahoor, et al.
Gepubliceerd in: (2024-09-01) -
Accurate Inference With Inaccurate RRAM Devices: A Joint Algorithm-Design Solution
door: Gouranga Charan, et al.
Gepubliceerd in: (2020-01-01)