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

Title: Optical beam classification using deep learning: a comparison with rule and feature based classification

; ; ;
Publication Date:
Research Org.:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Sponsoring Org.:
OSTI Identifier:
Report Number(s):
DOE Contract Number:
Resource Type:
Resource Relation:
Conference: Presented at: Optics and Photonics for Information Processing IX, San Diego, CA, United States, Aug 06 - Aug 08, 2017
Country of Publication:
United States

Citation Formats

Awwal, A, Alom, M Z, Webb, R L, and Raha, R. Optical beam classification using deep learning: a comparison with rule and feature based classification. United States: N. p., 2017. Web. doi:10.1117/12.2282903.
Awwal, A, Alom, M Z, Webb, R L, & Raha, R. Optical beam classification using deep learning: a comparison with rule and feature based classification. United States. doi:10.1117/12.2282903.
Awwal, A, Alom, M Z, Webb, R L, and Raha, R. Wed . "Optical beam classification using deep learning: a comparison with rule and feature based classification". United States. doi:10.1117/12.2282903.
title = {Optical beam classification using deep learning: a comparison with rule and feature based classification},
author = {Awwal, A and Alom, M Z and Webb, R L and Raha, R},
abstractNote = {},
doi = {10.1117/12.2282903},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Wed May 31 00:00:00 EDT 2017},
month = {Wed May 31 00:00:00 EDT 2017}

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:
  • Deep machine learning is an emerging framework for dealing with complex high-dimensionality data in a hierarchical fashion which draws some inspiration from biological sources. Despite the notable progress made in the field, there remains a need for an architecture that can represent temporal information with the same ease that spatial information is discovered. In this work, we present new results using a recently introduced deep learning architecture called Deep Spatio-Temporal Inference Network (DeSTIN). DeSTIN is a discriminative deep learning architecture that combines concepts from unsupervised learning for dynamic pattern representation together with Bayesian inference. In DeSTIN the spatiotemporal dependencies thatmore » exist within the observations are modeled inherently in an unguided manner. Each node models the inputs by means of clustering and simple dynamics modeling while it constructs a belief state over the distribution of sequences using Bayesian inference. We demonstrate that information from the different layers of this hierarchical system can be extracted and utilized for the purpose of pattern classification. Earlier simulation results indicated that the framework is highly promising, consequently in this work we expand DeSTIN to a popular problem, the MNIST data set of handwritten digits. The system as a preprocessor to a neural network achieves a recognition accuracy of 97.98% on this data set. We further show related experimental results pertaining to automatic cluster adaptation and termination.« less
  • Budgeted learning under constraints on both the amount of labeled information and the availability of features at test time pertains to a large number of real world problems. Ideas from multi-view learning, semi-supervised learning, and even active learning have applicability, but a common framework whose assumptions fit these problem spaces is non-trivial to construct. We leverage ideas from these fields based on graph regularizers to construct a robust framework for learning from labeled and unlabeled samples in multiple views that are non-independent and include features that are inaccessible at the time the model would need to be applied. We describemore » examples of applications that fit this scenario, and we provide experimental results to demonstrate the effectiveness of knowledge carryover from training-only views. As learning algorithms are applied to more complex applications, relevant information can be found in a wider variety of forms, and the relationships between these information sources are often quite complex. The assumptions that underlie most learning algorithms do not readily or realistically permit the incorporation of many of the data sources that are available, despite an implicit understanding that useful information exists in these sources. When multiple information sources are available, they are often partially redundant, highly interdependent, and contain noise as well as other information that is irrelevant to the problem under study. In this paper, we are focused on a framework whose assumptions match this reality, as well as the reality that labeled information is usually sparse. Most significantly, we are interested in a framework that can also leverage information in scenarios where many features that would be useful for learning a model are not available when the resulting model will be applied. As with constraints on labels, there are many practical limitations on the acquisition of potentially useful features. A key difference in the case of feature acquisition is that the same constraints often don't pertain to the training samples. This difference provides an opportunity to allow features that are impractical in an applied setting to nevertheless add value during the model-building process. Unfortunately, there are few machine learning frameworks built on assumptions that allow effective utilization of features that are only available at training time. In this paper we formulate a knowledge carryover framework for the budgeted learning scenario with constraints on features and labels. The approach is based on multi-view and semi-supervised learning methods that use graph-encoded regularization. Our main contributions are the following: (1) we propose and provide justification for a methodology for ensuring that changes in the graph regularizer using alternate views are performed in a manner that is target-concept specific, allowing value to be obtained from noisy views; and (2) we demonstrate how this general set-up can be used to effectively improve models by leveraging features unavailable at test time. The rest of the paper is structured as follows. In Section 2, we outline real-world problems to motivate the approach and describe relevant prior work. Section 3 describes the graph construction process and the learning methodologies that are employed. Section 4 provides preliminary discussion regarding theoretical motivation for the method. In Section 5, effectiveness of the approach is demonstrated in a series of experiments employing modified versions of two well-known semi-supervised learning algorithms. Section 6 concludes the paper.« less
  • The emergence and increasing prevalence of social media, such as internet forums, weblogs (blogs), wikis, etc., has created a new opportunity to measure public opinion, attitude, and social structures. A major challenge in leveraging this information is isolating the content and metadata in weblogs, as there is no standard, universally supported, machine-readable format for presenting this information. We present two algorithms for isolating this information. The first uses web block classification, where each node in the Document Object Model (DOM) for a page is classified according to one of several pre-defined attributes from a common blog schema. The second usesmore » a set of heuristics to select web blocks. These algorithms perform at a level suitable for initial use, validating this approach for isolating content and metadata from blogs. The resultant data serves as a starting point for analytical work on the content and substance of collections of weblog pages.« less
  • This paper presents the general framework of a multi level model to manage contaminated sites that is being developed. A rule based system along with a scoring system for ranking sites for phase 1 ESA is being proposed (Level 1). Level 2, which consists of the recommendation of the consultant based on their phase 1 ESA is reasonably straightforward. Level 3 which consists of classifying sites which already had a phase 2 ESA conducted on them will involve a multi-objective decision making tool. Fuzzy set theory, which includes the concept of membership functions, was adjudged as the best way tomore » deal with uncertain and non-random information. (authors)« less