Real-world applications of analog and digital evolvable hardware

Abstract

In contrast to conventional hardware where the structure is irreversibly fixed in the design process, evolvable hardware (EHW) is designed to adapt to changes in task requirements or changes in the environment, through its ability to reconfigure its own hardware structure dynamically and autonomously. This capacity for adaptation, achieved by employing efficient search algorithms based on the metaphor of evolution, has great potential for the development of innovative industrial applications. This paper introduces EHW chips and six applications currently being developed as part of MITI's Real-World Computing Project; an analog EHW chip for cellular phones, a clock-timing architecture for Giga hertz systems, a neural network EHW chip capable of autonomous reconfiguration, a data compression EHW chip for electrophotographic printers, and a gate-level EHW chip for use in prosthetic hands and robot navigation.

A Hardware Design of Neuromolecular Network with Enhanced Evolvability: A Bioinspired Approach

“…For example, the signal flows started at locations (1,5) and (8,7) may be integrated at location (5,5), and the readout enzyme at that location would be activated, thus causing a neuron firing. Because the integrated cytoskeletal signals may continuously appear, the firing outputs become a series of signals that happened in different time points.…”

“…Mange et al [4] successfully applied evolutionary techniques into the design of a timer (stopwatch) and a full watch (biowatch) with digital circuits. Higuchi and his colleagues [5,6] worked on the development of a number of evolvable hardware chips for various applications, including an analog chip for cellular phones, a clock-timing chip for Gigahertz systems, a chip for autonomous reconfiguration control, a data compression chip, and a chip for controlling robotic hands. Murakawa et al [7] applied evolutionary techniques to reconfigure neural network topology, de Garis [8,9] developed an artificial brain that assembled a group of cellular automatabased neural net modules to control a robot, and Torresen 2 Journal of Electrical and Computer Engineering [10] designed an evolutionary digital circuit to control prosthetic hands.…”

A fast Reconfigurable 2D HW core architecture on FPGAs for evolvable Self-Adaptive Systems

“…EH usually involves the use of reconfigurable hardware devices whose configuration is controlled by an EA [1]. EH is regarded like a key technology to achieve adaptive systems, that is, hardware systems able to reconfigure themselves to adapt to environmental or requirements changes, or to recover from faults.…”

“…Proposed by Higuchi [1] and De Garis [2] in 1993, EH research has split into various approaches, being online adaptive hardware the final objective of this work, which allows the automatic self-synthesis of new circuits by means of an Evolutionary Algorithm (EA) running in the system. However, integrating DPR with EH techniques suffers from the low speed of the reconfiguration ports.…”

A Flexible On-Chip Evolution System Implemented on a Xilinx Virtex-II Pro Device

“…This includes using evolution for invention of new hardware (circuits) to be included in conventional systems [20,22,25]. In the other end of the scale, evolution is used as a search algorithm for modifying or tuning parameters of already deployed, reconfigurable, hardware [12,32].…”