A configurable architecture for running hybrid convolutional neural networks in low-density FPGAs

Convolutional neural networks have become the state of the art of machine learning for a vast set of applications, especially for image classification and object detection. There are several advantages to running inference on these models at the edge, including real-time performance and data privacy...

Full description

Bibliographic Details
Main Author: Véstias, Mário (author)
Other Authors: Duarte, Rui (author), De Sousa, Jose (author), Cláudio de Campos Neto, Horácio (author)
Format: article
Language:eng
Published: 2021
Subjects:
Convolutional neural network
Deep learning
Embedded computing
Field-programmable gate array
Hybrid quantization
Online Access:http://hdl.handle.net/10400.21/12726
Country:Portugal
Oai:oai:repositorio.ipl.pt:10400.21/12726

Internet

http://hdl.handle.net/10400.21/12726

Similar Items