Hardware realization of BSB recall function using memristor crossbar arrays

• Published in: DAC Design Automation Conference 2012 pp. 498 - 503
• Main Authors: Hu, Miao, Li, Hai, Wu, Qing, Rose, Garrett S.
• Format: Conference Proceeding
• Language: English
• Published: New York, NY, USA ACM 03.06.2012; IEEE
• Series: ACM Conferences
• Subjects: Biological neural networks; Brain modeling; BSB model; Computer systems organization > Architectures > Other architectures > Neural networks; crossbar array; Integrated circuit modeling; memristor; Memristors; neural network; Neurons; Noise; process variation; Robustness; BSB model; crossbar array; neural network; process variation; memristor
• ISBN: 1450311997; 9781450311991
• ISSN: 0738-100X
• DOI: 10.1145/2228360.2228448

The Brain-State-in-a-Box (BSB) model is an auto-associative neural network that has been widely used in optical character recognition and image processing. Traditionally, the BSB model was realized at software level and carried out on high-performance computing clusters. To improve computation efficiency and reduce resources requirement, we propose a hardware realization by utilizing memristor crossbar arrays. In this work, we explore the potential of a memristor crossbar array as an auto-associative memory. More specificly, the recall function of a multi-answer character recognition based on BSB model was realized. The robustness of the proposed BSB circuit was analyzed and evaluated based on massive Monte-Carlo simulations, considering input defects, process variations, and electrical fluctuations. The physical constrains when implementing a neural network with memristor crossbar array have also been discussed. Our results show that the BSB circuit has a high tolerance to random noise. Comparably, the correlations between memristor arrays introduces directional noise and hence dominates the quality of circuits.