What is it about?
Optimization of Convolutional Neural Networks on Resource-Constrained Devices, and implementation on FPGA
Featured Image
Why is it important?
Implementation of convolutional neural networks (CNNs) on resource-constrained devices like FPGA (example: Zynq) etc. is important for intelligence in edge computing. This paper presents and discusses different hardware optimization methods that were employed to design a CNN model that is amenable to such devices, in general. Adaptive processing, exploitation of parallelism, etc. are employed to show the superior performance of proposed methods over state of the art.
Perspectives
Convolutional neural networks are computationally intensive and inferencing CNNs on resource-constrained devices without adversely affecting the performance is a difficult task for hardware designers. This work shows an efficient technique to optimize CNNs to embed it on resource-constrained FPGAs.
Arish Sateesan
Katholieke Universiteit Leuven
Read the Original
This page is a summary of: Optimization of Convolutional Neural Networks on Resource Constrained Devices, July 2019, Institute of Electrical & Electronics Engineers (IEEE),
DOI: 10.1109/isvlsi.2019.00013.
You can read the full text:
Contributors
The following have contributed to this page
