Implementation issues of neuro-fuzzy hardware: going toward HW/SW codesign

Abstract

This paper presents an annotated overview of existing hardware implementations of artificial neural and fuzzy systems and points out limitations, advantages, and drawbacks of analog, digital, pulse stream (spiking), and other implementation techniques. We analyze hardware performance parameters and tradeoffs, and the bottlenecks which are intrinsic in several implementation methodologies. The constraints posed by hardware technologies onto algorithms and performance are also described. The results of the analyses proposed lead to the use of hardware/software codesign, as a means of exploiting the best from both hardware and software techniques. Hardware/software codesign appears, at present, the most promising research area concerning the implementation of neuro-fuzzy systems (not including bioinspired systems, which are out of the scope of this work), as it allows the fast design of complex systems with the highest performance/cost ratio.

FPGA Implementation of Embedded Fuzzy Controllers for Robotic Applications

“…These approaches range from fully software or hardware solutions to hybrid strategies that allow reaching adequate tradeoffs between flexibility and inference speed [3]. Hybrid realizations require a processor for software task execution and dedicated hardware for implementing complex time-consuming tasks, i.e., usually the fuzzy inference process.…”

Towards Hardware Acceleration of Neuroevolution for Multimedia Processing Applications on Mobile Devices

“…Our profiling has revealed the computational burden of the ANN evaluation is suitable for hardware off load, whilst the genetic algorithm routines, which use moderate computational resources can reside in software. This scalable co-design methodology combines the reconfigurability of software with the speed of hardware [5]. This also facilitates application re-usability, where the core could be re-deployed for a number of applications.…”

Design of Near-Optimal Classifier Using Multi-Layer Perceptron Neural Networks for Intelligent Sensors

“…The advancement of FPGAs in recent years, allowing millions of gates on a single chip and accompanying with high-level design tools has allowed the implementation of very complex neural networks [14]. It allows the fast design of complex systems with the highest performance/cost ratio [15]. FPGA is the most suitable hardware for neural networks implementation as it preserves the parallel architecture of the neurons and can be flexibly reconfigured by the user as the application demands.…”