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...
Główni autorzy: | Tayfun Gokmen, Murat Onen, Wilfried Haensch |
---|---|
Format: | Artykuł |
Język: | English |
Wydane: |
Frontiers Media S.A.
2017-10-01
|
Seria: | Frontiers in Neuroscience |
Hasła przedmiotowe: | |
Dostęp online: | http://journal.frontiersin.org/article/10.3389/fnins.2017.00538/full |
Podobne zapisy
-
Training LSTM Networks With Resistive Cross-Point Devices
od: Tayfun Gokmen, i wsp.
Wydane: (2018-10-01) -
MR-PIPA: An Integrated Multilevel RRAM (HfO<sub><italic>x</italic></sub>)-Based Processing-In-Pixel Accelerator
od: Minhaz Abedin, i wsp.
Wydane: (2022-01-01) -
Reliable and Energy-Efficient Diabetic Retinopathy Screening Using Memristor-Based Neural Networks
od: Sumit Diware, i wsp.
Wydane: (2024-01-01) -
Design implementations of ternary logic systems: A critical review
od: Furqan Zahoor, i wsp.
Wydane: (2024-09-01) -
Accurate Inference With Inaccurate RRAM Devices: A Joint Algorithm-Design Solution
od: Gouranga Charan, i wsp.
Wydane: (2020-01-01)