VLSI-Friendly Filtering Algorithms for Deep Neural Networks

VLSI-Friendly Filtering Algorithms for Deep Neural Networks

The paper introduces a range of efficient algorithmic solutions for implementing the fundamental filtering operation in convolutional layers of convolutional neural networks on fully parallel hardware. Specifically, these operations involve computing <i>M</i> inner products between neigh...

Full description

Bibliographic Details
Main Authors: Aleksandr Cariow, Janusz P. Papliński, Marta Makowska
Format: Article
Language:English
Published: MDPI AG 2023-08-01
Series:Applied Sciences
Subjects:
filtering algorithms
deep neural networks
very large-scale integration
multiplicative complexity
Online Access:https://www.mdpi.com/2076-3417/13/15/9004

Internet

https://www.mdpi.com/2076-3417/13/15/9004

Similar Items