Memristor‐Based Analog Computation and Neural Network Classification with a Dot Product Engine
By Miao Hu, Catherine E. Graves, Can Li, Yunning Li, Ning Ge, Eric Montgomery, N. Dávila, Hao Jiang, R. S. Williams, J. Joshua Yang and 2 more. Advances in Materials, 2018
676 citations recorded by the source corpus.
Subfields: Cellular and Molecular Neuroscience, Electrical and Electronic Engineering
View Paper: https://www.semanticscholar.org/paper/19c23c5fe58dd5e027d136219327e54276425353
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Cellular and Molecular Neuroscience
In Electrical and Electronic Engineering
- John Paul Strachan
- R. S. Williams
- Michael Hochberg
- T. Baehr‐Jones
- Kaushik Roy
- Dirk Englund
- Nicholas Christopher Harris
- Mihika Prabhu
Citations in the corpus
- PUMA: A Programmable Ultra-efficient Memristor-based Accelerator for Machine Learning Inference (2019, methodology): “result. They are integrated (converted to voltage) then converted to digital values with ADCs. 3.2.1 Precision Considerations Practically realizable crossbars provide 2-6 bits of precision per device [52]. We conservatively use 2 bits per device, and realize 16-bit MVM operations by combining 8 cros”
- Linear programmable nanophotonic processors (2018, background): “Some machine learning algorithms, including neural networks, appear suited for analog computing architectures, including analog complementary metal-oxide semiconductor (CMOS) circuits [69], memristor arrays [70,71], photonic networks [2], and magnetic devices [72].”
- Hardware implementation of memristor-based artificial neural networks (2024, neutral): “A cost-effective recurrent solution has been to use a smaller number of DACs and share them among different rows by adding a layer of analogue multiplexors between the DACs and the wordline inputs 93,95,221 .”