Donna Harman
ABSTRACT
A critical piece of evaluation is doing a failure analysis of the experimental results. This is necessary to improve results, but equally important, it is necessary to understand where the problems REALLY are, as opposed to just following "conventional" wisdom. The talk will present some current failure analysis techniques and examine how these techniques could be extended to retrieval from noisy data.
Index Terms
- Some thoughts on failure analysis for noisy data
Recommendations
A Novel Data Analysis Methodology in Failure Analysis
ISDEA '12: Proceedings of the 2012 Second International Conference on Intelligent System Design and Engineering ApplicationIn Semiconductor IC failure analysis, failure localization is the most important step. However, as semiconductor circuits get more complex and devices trend to smaller dimension, failure localization becomes very difficult if failure is not caused ...
Reliability analysis on competitive failure processes under fuzzy degradation data
Reliability is the ability of a system to perform its required functions under stated conditions for a specified period of time. Reliability analysis is an important tool to evaluate the performance of a system and make maintenance decision. In ...
Some thoughts on undergraduate teaching and the Ph.D.
As the hiring crisis in academic computer science worsens, many people ask whether faculty whose primary job is teaching need doctorates. In the past, the answer would have been "yes;" now people increasingly suggest that it could be "no." I have argued ...
Comments