Parametric optimization of reconfigurable designs using machine learning

Authors:
Maciej Kurek;Tobias Becker;Wayne Luk
Affiliations:
Department of Computing, Imperial College London, UK;Department of Computing, Imperial College London, UK;Department of Computing, Imperial College London, UK
Venue:
ARC'13 Proceedings of the 9th international conference on Reconfigurable Computing: architectures, tools, and applications
Year:
2013

Citing 9
Cited 0

An analysis of particle swarm optimizers

An analysis of particle swarm optimizers
Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)

Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
Improving evolutionary exploration to area-time optimization of FPGA designs

Journal of Systems Architecture: the EUROMICRO Journal
Gaussian Process Assisted Differential Evolution Algorithm for Computationally Expensive Optimization Problems

PACIIA '08 Proceedings of the 2008 IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application - Volume 01
Parametric Design for Reconfigurable Software-Defined Radio

ARC '09 Proceedings of the 5th International Workshop on Reconfigurable Computing: Architectures, Tools and Applications
A Cooperative Optimization Algorithm Based on Gaussian Process and Particle Swarm Optimization for Optimizing Expensive Problems

CSO '09 Proceedings of the 2009 International Joint Conference on Computational Sciences and Optimization - Volume 02
A framework for evolutionary optimization with approximate fitnessfunctions

IEEE Transactions on Evolutionary Computation
Optimising performance of quadrature methods with reduced precision

ARC'12 Proceedings of the 8th international conference on Reconfigurable Computing: architectures, tools and applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a novel technique that uses meta- heuristics and machine learning to automate the optimization of design parameters for reconfigurable designs. Traditionally, such an optimization involves manual application analysis as well as model and parameter space exploration tool creation. We develop a Machine Learning Optimizer (MLO) to automate this process. From a number of benchmark executions, we automatically derive the characteristics of the parameter space and create a surrogate fitness function through regression and classification. Based on this surrogate model, design parameters are optimized with meta-heuristics. We evaluate our approach using two case studies, showing that the number of benchmark evaluations can be reduced by up to 85% compared to previously performed manual optimization.