Vector multiplications using memristive devices
Abstract
Modern deep learning architectures, depend heavily on vector-matrix multiplications (VMMs), which serve as the foundational computational operation for each layer in deep neural networks. Within these VMMs, non-linear activation functions, such as rectified linear units or sigmoid functions, play a critical role.
Fields of Study & Subjects
Advanced Memory and Neural Computing
Ferroelectric and Negative Capacitance Devices
Neural Networks and Reservoir Computing
Publication details
- Pages
- 6–1
- Publication date
- 1 January 2026
- Document type
- Book chapter