Machine learning on FPGA CAD

Parameter tuning for field-programmable gate array (FPGA) computer-aided design (CAD) tools was a difficult task. Plunify proposed a novel solution by incorporating machine learning. A classifier was built and refined iteratively from CAD run records; and it was used to predict whether a new set of...

Full description

Saved in:
Bibliographic Details
Main Author: Que, Yanghua
Other Authors: Nachiket Kapre
Format: Final Year Project
Language:English
Published: 2015
Subjects:
Online Access:http://hdl.handle.net/10356/65738
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-65738
record_format dspace
spelling sg-ntu-dr.10356-657382023-03-03T20:35:17Z Machine learning on FPGA CAD Que, Yanghua Nachiket Kapre School of Computer Engineering DRNTU::Engineering::Electrical and electronic engineering Parameter tuning for field-programmable gate array (FPGA) computer-aided design (CAD) tools was a difficult task. Plunify proposed a novel solution by incorporating machine learning. A classifier was built and refined iteratively from CAD run records; and it was used to predict whether a new set of parameters would produce a good design. The machine learning routine has been proven effective; and this paper is an extension aimed to improve performance of the method. We experimented with feature selection and discovered only about 10-20 parameters in the group of 60 were relevant. We also constructed ensemble classifiers that helped to drive Area Under Curve (AUC) score from 0.75 to 0.79; and we further pushed the number to 0.82 when combining ensemble learning and feature selection. Bachelor of Engineering (Computer Science) 2015-12-10T09:01:55Z 2015-12-10T09:01:55Z 2015 2015 Final Year Project (FYP) http://hdl.handle.net/10356/65738 en Nanyang Technological University application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Electrical and electronic engineering
spellingShingle DRNTU::Engineering::Electrical and electronic engineering
Que, Yanghua
Machine learning on FPGA CAD
description Parameter tuning for field-programmable gate array (FPGA) computer-aided design (CAD) tools was a difficult task. Plunify proposed a novel solution by incorporating machine learning. A classifier was built and refined iteratively from CAD run records; and it was used to predict whether a new set of parameters would produce a good design. The machine learning routine has been proven effective; and this paper is an extension aimed to improve performance of the method. We experimented with feature selection and discovered only about 10-20 parameters in the group of 60 were relevant. We also constructed ensemble classifiers that helped to drive Area Under Curve (AUC) score from 0.75 to 0.79; and we further pushed the number to 0.82 when combining ensemble learning and feature selection.
author2 Nachiket Kapre
author_facet Nachiket Kapre
Que, Yanghua
format Final Year Project
author Que, Yanghua
author_sort Que, Yanghua
title Machine learning on FPGA CAD
title_short Machine learning on FPGA CAD
title_full Machine learning on FPGA CAD
title_fullStr Machine learning on FPGA CAD
title_full_unstemmed Machine learning on FPGA CAD
title_sort machine learning on fpga cad
publishDate 2015
url http://hdl.handle.net/10356/65738
_version_ 1759853039971205120