A Brain-Inspired Hardware Architecture for Evolutionary Algorithms based on Memristive Arrays

Brain-inspired computing takes inspiration from the brain to create energy-efficient hardware systems for information processing, capable of performing highly sophisticated tasks. Systems built with emerging electronics, such as memristive devices, can achieve gains in speed and energy by mimicking distributed topology brain. In this work, a brain-inspired architecture evolutionary algorithms is proposed based on arrays, which realize sparse approximate result parallel analog characteristic arrays. On basis, an efficient evolvable system implemented. We experimentally show that approach offer at least four orders magnitude improvement. also use grounded simulations explore fault tolerance different parameter settings implemented system. The experimental results system, architecture, continuously evolve towards better even if there are failures or changes demonstrating has good adaptability tolerance.