A dynamically-reconfigurable FPGA platform for evolving fuzzy systems

Authors:
Grégory Mermoud;Andres Upegui;Carlos-Andres Peña;Eduardo Sanchez
Affiliations:
Logic Systems Laboratory – LSL, Ecole Polytechnique Fédérale de Lausanne – EPFL, Lausanne, Switzerland;Logic Systems Laboratory – LSL, Ecole Polytechnique Fédérale de Lausanne – EPFL, Lausanne, Switzerland;Novartis Institutes for Biomedical Research – NIBR, Basel, Switzerland;Logic Systems Laboratory – LSL, Ecole Polytechnique Fédérale de Lausanne – EPFL, Lausanne, Switzerland
Venue:
IWANN'05 Proceedings of the 8th international conference on Artificial Neural Networks: computational Intelligence and Bioinspired Systems
Year:
2005

Citing 2
Cited 5

Field-Programmable Gate Array Technology

Field-Programmable Gate Array Technology
Implementation of evolutionary fuzzy systems

IEEE Transactions on Fuzzy Systems

On-chip and on-line self-reconfigurable adaptable platform: the non-uniform cellular automata case

IPDPS'06 Proceedings of the 20th international conference on Parallel and distributed processing
FPGA implementation of fuzzy system with parametric membership functions and parametric conjunctions

MICAI'10 Proceedings of the 9th Mexican international conference on Artificial intelligence conference on Advances in soft computing: Part II
Fuzzy logic hardware implementation for pneumatic control of one DOF pneumatic robot

MICAI'10 Proceedings of the 9th Mexican international conference on Artificial intelligence conference on Advances in soft computing: Part II
Evolving hardware by dynamically reconfiguring xilinx FPGAs

ICES'05 Proceedings of the 6th international conference on Evolvable Systems: from Biology to Hardware
On the monotone sum of basic t-norms in the construction of parametric families of digital conjunctors for fuzzy systems with reconfigurable logic

Knowledge-Based Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this contribution, we describe a hardware platform for evolving a fuzzy system by using Fuzzy CoCo — a cooperative coevolutionary methodology for fuzzy system design — in order to speed up both evolution and execution. Reconfigurable hardware arises between hardware and software solutions providing a trade-off between flexibility and performance. We present an architecture that exploits the dynamic partial reconfiguration capabilities of recent FPGAs so as to provide adaptation at two different levels: major structural changes and fuzzy parameter tuning.