skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Experience with machine learning in accelerator controls

Authors:
; ; ; ; ;
Publication Date:
Research Org.:
Brookhaven National Laboratory (BNL), Upton, NY (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Nuclear Physics (NP) (SC-26)
OSTI Identifier:
1402419
Report Number(s):
BNL-113753-2017-CP
R&D Project: KBCH139; 18070; KB0202011
DOE Contract Number:
SC0012704
Resource Type:
Conference
Resource Relation:
Conference: 16th International Conference on Accelerator and Large Experimental Physics Control Systems (ICALEPCS 2017); Barcelona, Spain; 20171008 through 20171013
Country of Publication:
United States
Language:
English
Subject:
43 PARTICLE ACCELERATORS

Citation Formats

Brown K. A., Binello, S., D Ottavio, T., Dyer, P.S., Nemesure, S., and Thomas, D. J. Experience with machine learning in accelerator controls. United States: N. p., 2017. Web.
Brown K. A., Binello, S., D Ottavio, T., Dyer, P.S., Nemesure, S., & Thomas, D. J. Experience with machine learning in accelerator controls. United States.
Brown K. A., Binello, S., D Ottavio, T., Dyer, P.S., Nemesure, S., and Thomas, D. J. Sun . "Experience with machine learning in accelerator controls". United States. doi:. https://www.osti.gov/servlets/purl/1402419.
@article{osti_1402419,
title = {Experience with machine learning in accelerator controls},
author = {Brown K. A. and Binello, S. and D Ottavio, T. and Dyer, P.S. and Nemesure, S. and Thomas, D. J.},
abstractNote = {},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Sun Oct 08 00:00:00 EDT 2017},
month = {Sun Oct 08 00:00:00 EDT 2017}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • Abstract not provided.
  • This book contains over 30 selections. Some of the titles are: Decision Trees as Probabilitic Classifers; Conceptual Clustering, Learning from Examples, and Inference; QuasiDarwinian Learning in a Classifier System; Concept Learning in Context; and a New Approach to Unsupervised Learning in Deterministic Environments.
  • Knowledge-based remote sensing image analysis with GIS data is acknowledged as a promising technique. However, the difficulty in knowledge acquisition, a well-known bottleneck in building knowledge-based systems, impedes the adoption of this technique. Automating knowledge acquisition is therefore in demand. This paper presents a machine learning approach to automated construction of knowledge bases for image analysis expert systems integrating remotely sensed and GIS data. The methodology applied in the study is based on inductive learning techniques in machine learning, a subarea of artificial intelligence. It involves training with examples from remote sensing and GIS data, learning using the inductive principles,more » decision tree generating, rule generating from the decision tree, and knowledge base building for an image analysis expert system. This method was used to construct a knowledge base for wetland classification of Par Pond on the Savannah River Site, SC, using SPOT image data and GIS data. The preliminary results show that this method can provide an effective approach to integration of remotely sensed and GIS data in geographic information processing.« less
  • This tutorial was one of eight tutorials selected to be presented at the Third International Conference on Intelligent Systems for Molecular Biology which was held in the United Kingdom from July 16 to 19, 1995. Computational tools are increasingly needed to process the massive amounts of data, to organize and classify sequences, to detect weak similarities, to separate coding from non-coding regions, and reconstruct the underlying evolutionary history. The fundamental problem in machine learning is the same as in scientific reasoning in general, as well as statistical modeling: to come up with a good model for the data. In thismore » tutorial four classes of models are reviewed. They are: Hidden Markov models; artificial Neural Networks; Belief Networks; and Stochastic Grammars. When dealing with DNA and protein primary sequences, Hidden Markov models are one of the most flexible and powerful alignments and data base searches. In this tutorial, attention is focused on the theory of Hidden Markov Models, and how to apply them to problems in molecular biology.« less
  • We address three problems in machine learning, namely: (i) function learning, (ii) regression estimation, and (iii) sensor fusion, in the Probably and Approximately Correct (PAC) framework. We show that, under certain conditions, one can reduce the three problems above to the regression estimation. The latter is usually tackled with artificial neural networks (ANNs) that satisfy the PAC criteria, but have high computational complexity. We propose several computationally efficient PAC alternatives to ANNs to solve the regression estimation. Thereby we also provide efficient PAC solutions to the function learning and sensor fusion problems. The approach is based on cross-fertilizing concepts andmore » methods from statistical estimation, nonlinear algorithms, and the theory of computational complexity, and is designed as part of a new, coherent paradigm for machine learning.« less