@inproceedings{8b91d50bc6c3476f857737493ee8318d,
title = "Failure Analysis of Large Area Pt/HfO2/Pt Capacitors Using Multilayer Perceptrons",
abstract = "In this work, we investigated the spatial distribution of failure sites in large area Pt/HfO2/Pt capacitors using simple neural networks as classifiers. When an oxide breakdown (BD) occurs due to severe electrical stress, a mark shows up in the top metal electrode at the location where the failure event took place. The mark is the result of a microexplosion occurring inside the dielectric film. Large area devices need to be studied because the number of generated spots must be the required for statistical analysis. The obtained results using multilayer perceptrons with different number of neurons and hidden layers indicate that the largest breakdown spots tend to concentrate towards the center of the device. This observation is consistent with previous exploratory analysis carried out using spatial statistics techniques. This exercise shows the suitability of multilayer perceptrons for investigating the distribution of failure sites or defects on a given surface.",
keywords = "dielectric breakdown, MIM, neural networks, perceptron, reliability, spatial statistics",
author = "J. Munoz-Gorriz and S. Monaghan and K. Cherkaoui and J. Sune and Hurley, \{P. K.\} and E. Miranda",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits, IPFA 2021 ; Conference date: 15-09-2021 Through 15-10-2021",
year = "2021",
doi = "10.1109/IPFA53173.2021.9617281",
language = "English",
series = "Proceedings of the International Symposium on the Physical and Failure Analysis of Integrated Circuits, IPFA",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2021 IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits, IPFA 2021",
address = "United States",
}