Weight Update Generation Circuit Utilizing Phase Noise of Integrated Complementary Metal–Oxide–Semiconductor Ring Oscillator for Memristor Crossbar Array Neural Network‐Based Stochastic Learning. (27th March 2020)

• Record Type: Journal Article
• Authors: Bae, Woorham; Yoon, Kyung Jean
• Is Part Of: Advanced intelligent systems. Volume 2:Number 5(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-03-27
• Subjects: crossbar neural networks -- memristors -- oscillator phase noise -- stochastic learning -- weight generation circuits; Artificial intelligence -- Periodicals; Robotics -- Periodicals; Control theory -- Periodicals; 006.3
• DOI: 10.1002/aisy.202000011
• Languages: English
• ISSNs: 2640-4567

Abstract

Abstract : Herein, a robust programmable stochastic weight generation method for a memristive neural network is proposed. There have been few prior algorithm suggestions for crossbar neural network‐based stochastic learning; however, there has not been much attention focussed on robust physical implementations. As a result, coming up with a robust method to provide the probability generator is an essential knob for its physical implementation. Here, implanting such stochastic behavior into the weight update signal itself is proposed, by multiplying it with the randomized probability sequence. To generate such probability sequence, bang‐bang dithering of a phase‐locked loop (PLL) with a binary phase detector (PD) is used. The programmable probability is enabled by introducing an offset for the PD outputs. Yet the dithering sequence has deterministic nature, phase noise of complementary metal–oxide–semiconductor (CMOS) ring oscillator to randomize the deterministic dithering is exploited. As a result, this lower power oscillator offers a better probability sequence, which enables an ultralow power circuit implementation. Abstract : A probability generator dedicated for stochastic learning in memristor cross‐point array‐based neural network is presented. It mainly utilizes the intrinsic noise of a complementary metal–oxide–semiconductor (CMOS) ring oscillator, which not only benefits from a robust and practical solution but also from an ultralow power consumption in comparison to the methods proposed in prior works.