Hardware implementation of memristor-based artificial neural networks
Universitat Autònoma de Barcelona · King Abdullah University of Science and Technology · +11 more institutions
Abstract
Artificial Intelligence (AI) is currently experiencing a bloom driven by deep learning (DL) techniques, which rely on networks of connected simple computing units operating in parallel. The low communication bandwidth between memory and processing units in conventional von Neumann machines does not support the requirements of emerging applications that rely extensively on large sets of data. More recent computing paradigms, such as high parallelization and near-memory computing, help alleviate the data communication bottleneck to some extent, but paradigm- shifting concepts are required. Memristors, a novel beyond-complementary metal-oxide-semiconductor (CMOS) technology, are a promising choice for memory…
Citation impact
- FWCI
- 75.56
- Percentile
- 100%
- References
- 274
Authors
31Topics & keywords
- Memristor
- Computer science
- Artificial neural network
- Physical neural network
- Artificial intelligence
- Computer architecture
- Types of artificial neural networks
- Time delay neural network
- Affordable and clean energy
Funding
- UOUniversity of Southern California
- UCUniversity College London
- NUNational University of Singapore
- KAKing Abdullah University of Science and Technology
- MDMinisterio de Ciencia e InnovaciónAwards: FJC2021-046808-I, PID2022
- NTNational Tsing Hua University
- UDUniversidad de Granada
- PUPeking University
- HUHebei University
- UAUniversitat Autònoma de Barcelona
- DODivision of Mathematical Sciences