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

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.

Simulink-based HW/SW codesign of embedded neuro-fuzzy systems.

We propose a semi-automatic HW/SW codesign flow for low-power and low-cost Neuro-Fuzzy embedded systems. Applications range from fast prototyping of embedded systems to high-speed simulation of Simulink models and rapid design of Neuro-Fuzzy devices. The proposed codesign flow works with different technologies and architectures (namely, software, digital and analog). We have used The Mathworks' Simulink environment for functional specification and for analysis of performance criteria such as timing (latency and throughput), power dissipation, size and cost. The proposed flow can exploit trade-offs between SW and HW as well as between digital and analog implementations, and it can generate, respectively, the C, VHDL and SKILL codes of the selected architectures.

Unification of neural and wavelet networks and fuzzy systems.

This paper analyzes several commonly used soft computing paradigms (neural and wavelet networks and fuzzy systems, Bayesian classifiers, fuzzy partitions, etc.) and tries to outline similarities and differences among each other. These are exploited to produce the weighted radial basis functions paradigm which may act as a neuro-fuzzy unification paradigm. Training rules (both supervised and unsupervised) are also unified by the proposed algorithm. Analyzing differences and similarities among existing paradigms helps to understand that many soft computing paradigms are very similar to each other and can be grouped in just two major classes. The many reasons to unify soft computing paradigms are also shown in the paper. A conversion method is presented to convert perceptrons, radial basis functions, wavelet networks, and fuzzy systems from each other.

Using coherent pulse width and edge modulations in artificial neural systems.

This paper describes an existing silicon implementation of an artificial neural system based on coherent pulse width and edge modulation techniques. A chip set with different neural functions has been conceived, manufactured and tested. Neural circuits have been optimized for lowest computation energy and highest reconfigurability. The main device is a 32 x 32 synaptic array consuming 10 mW of power at 140 MCPS. Synapsis size is about 7.200 microns 2 using a standard 1.5 microns CMOS technology. The problem of interfacing robotic sensors and actuators is addressed: voltage, current and resistance-based sensors are considered for the measurement of physical quantities such as temperature, pressure, strain, etc. Low resolution imaging sensors for robotic vision are also considered.