Machine Learning Based Lithography Hotspot Detection with Sparse Feature Encoding and Hierarchical Pattern Classification

2014 ◽  
Vol 60 (1) ◽  
pp. 1179-1184 ◽  
Author(s):  
K. s. Luo ◽  
Z. Shi ◽  
Z. Geng
Keyword(s):  
Machine Learning ◽  
Pattern Classification ◽  
Hotspot Detection ◽  
Feature Encoding ◽  
Hierarchical Pattern

Classification with Incomplete Data

2010 ◽  
pp. 147-175 ◽  
Author(s):  
Pedro J. García-Laencina ◽  
Juan Morales-Sánchez ◽  
Rafael Verdú-Monedero ◽  
Jorge Larrey-Ruiz ◽  
José-Luis Sancho-Gómez ◽  
...  
Keyword(s):  
Machine Learning ◽  
Missing Data ◽  
Pattern Classification ◽  
Incomplete Data ◽  
Data Handling ◽  
Advantages And Disadvantages ◽  
Word Classification ◽  
Classification Tasks ◽  
Missing Data Techniques ◽  
Fundamental Requirement

Many real-word classification scenarios suffer a common drawback: missing, or incomplete, data. The ability of missing data handling has become a fundamental requirement for pattern classification because the absence of certain values for relevant data attributes can seriously affect the accuracy of classification results. This chapter focuses on incomplete pattern classification. The research works on this topic currently grows wider and it is well known how useful and efficient are most of the solutions based on machine learning. This chapter analyzes the most popular and proper missing data techniques based on machine learning for solving pattern classification tasks, trying to highlight their advantages and disadvantages.

scholarly journals In Vivo Pattern Classification of Ingestive Behavior in Ruminants Using FBG Sensors and Machine Learning

Sensors ◽  
2015 ◽  
Vol 15 (11) ◽  
pp. 28456-28471 ◽  
Author(s):  
Vinicius Pegorini ◽  
Leandro Zen Karam ◽  
Christiano Pitta ◽  
Rafael Cardoso ◽  
Jean da Silva ◽  
...  
Keyword(s):  
Machine Learning ◽  
Pattern Classification ◽  
Ingestive Behavior ◽  
Fbg Sensors

Machine learning for mask/wafer hotspot detection and mask synthesis

2017 ◽  
Author(s):  
David Z. Pan ◽  
Yibo Lin ◽  
Xiaoqing Xu ◽  
Jiaojiao Ou
Keyword(s):  
Machine Learning ◽  
Hotspot Detection

scholarly journals Exploring the limitations of biophysical propensity scales coupled with machine learning for protein sequence analysis

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Daniele Raimondi ◽  
Gabriele Orlando ◽  
Wim F. Vranken ◽  
Yves Moreau
Keyword(s):  
Machine Learning ◽  
Protein Sequence ◽  
Feature Learning ◽  
Structural Bioinformatics ◽  
Protein Sequence Analysis ◽  
Learning Problem ◽  
Functional Aspects ◽  
Feature Encoding ◽  
Non Linear ◽  
Optimal Feature

AbstractMachine learning (ML) is ubiquitous in bioinformatics, due to its versatility. One of the most crucial aspects to consider while training a ML model is to carefully select the optimal feature encoding for the problem at hand. Biophysical propensity scales are widely adopted in structural bioinformatics because they describe amino acids properties that are intuitively relevant for many structural and functional aspects of proteins, and are thus commonly used as input features for ML methods. In this paper we reproduce three classical structural bioinformatics prediction tasks to investigate the main assumptions about the use of propensity scales as input features for ML methods. We investigate their usefulness with different randomization experiments and we show that their effectiveness varies among the ML methods used and the tasks. We show that while linear methods are more dependent on the feature encoding, the specific biophysical meaning of the features is less relevant for non-linear methods. Moreover, we show that even among linear ML methods, the simpler one-hot encoding can surprisingly outperform the “biologically meaningful” scales. We also show that feature selection performed with non-linear ML methods may not be able to distinguish between randomized and “real” propensity scales by properly prioritizing to the latter. Finally, we show that learning problem-specific embeddings could be a simple, assumptions-free and optimal way to perform feature learning/engineering for structural bioinformatics tasks.

scholarly journals QUATgo: Protein quaternary structural attributes predicted by two-stage machine learning approaches with heterogeneous feature encoding

PLoS ONE ◽  
2020 ◽  
Vol 15 (4) ◽  
pp. e0232087
Author(s):  
Chi-Hua Tung ◽  
Ching-Hsuan Chien ◽  
Chi-Wei Chen ◽  
Lan-Ying Huang ◽  
Yu-Nan Liu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Learning Approaches ◽  
Two Stage ◽  
Feature Encoding ◽  
Heterogeneous Feature

Litho-Aware Machine Learning for Hotspot Detection

2018 ◽  
Vol 37 (7) ◽  
pp. 1510-1514 ◽  
Author(s):  
Jea Woo Park ◽  
Andres Torres ◽  
Xiaoyu Song
Keyword(s):  
Machine Learning ◽  
Hotspot Detection
Sign in / Sign up

Export Citation Format

Share Document