D-NAT: Data-Driven Non-Ideality Aware Training Framework for Fabricated Computing-In-Memory Macros
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Journal on Emerging and Selected Topics in Circuits and Systems"
DOI: 10.1109/jetcas.2022.3171268
Abstract: To enable energy-efficient computation for deep neural networks (DNNs) at edge, computing-in-memory (CIM) is proposed to reduce the energy costs during intense off-chip memory access. However, CIM is prone to multiply-accumulate (MAC) errors due to… read more here.
Keywords: non idealities; framework; data driven; driven non ... See more keywords
A Non-Idealities Aware Software–Hardware Co-Design Framework for Edge-AI Deep Neural Network Implemented on Memristive Crossbar
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Journal on Emerging and Selected Topics in Circuits and Systems"
DOI: 10.1109/jetcas.2022.3214334
Abstract: In this work, a non-idealities aware software-hardware co-design framework for deep neural network (DNN) implemented on memristive crossbar is presented. The device level non-ideal factors such as device conductance variation, nonuniform quantization levels, device-to-device variation… read more here.
Keywords: neural network; network; framework; non idealities ... See more keywords
Analysis of non-idealities in rhomb compensators.
Sign Up to like & getrecommendations! Published in 2021 at "Optics express"
DOI: 10.1364/oe.440680
Abstract: In-line rotatable rhombs that are only weakly chromatic are desired as compensators for a wide variety of applications in spectroscopic polarimetry and Mueller matrix spectroscopic ellipsometry. These devices employ multiple total internal reflections to generate… read more here.
Keywords: rhomb compensators; idealities rhomb; non idealities; stress induced ... See more keywords