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...
主要な著者: | Tayfun Gokmen, Murat Onen, Wilfried Haensch |
---|---|
フォーマット: | 論文 |
言語: | English |
出版事項: |
Frontiers Media S.A.
2017-10-01
|
シリーズ: | Frontiers in Neuroscience |
主題: | |
オンライン・アクセス: | http://journal.frontiersin.org/article/10.3389/fnins.2017.00538/full |
類似資料
-
Training LSTM Networks With Resistive Cross-Point Devices
著者:: Tayfun Gokmen, 等
出版事項: (2018-10-01) -
MR-PIPA: An Integrated Multilevel RRAM (HfO<sub><italic>x</italic></sub>)-Based Processing-In-Pixel Accelerator
著者:: Minhaz Abedin, 等
出版事項: (2022-01-01) -
Reliable and Energy-Efficient Diabetic Retinopathy Screening Using Memristor-Based Neural Networks
著者:: Sumit Diware, 等
出版事項: (2024-01-01) -
Design implementations of ternary logic systems: A critical review
著者:: Furqan Zahoor, 等
出版事項: (2024-09-01) -
Accurate Inference With Inaccurate RRAM Devices: A Joint Algorithm-Design Solution
著者:: Gouranga Charan, 等
出版事項: (2020-01-01)