Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Discipline
Articles 1 - 6 of 6
Full-Text Articles in Physical Sciences and Mathematics
Reducing The Manual Annotation Effort For Handwriting Recognition Using Active Transfer Learning, Eric Burdett
Reducing The Manual Annotation Effort For Handwriting Recognition Using Active Transfer Learning, Eric Burdett
Theses and Dissertations
Handwriting recognition systems have achieved remarkable performance over the past several years with the advent of deep neural networks. For high-quality recognition, these models require large amounts of labeled training data, which can be difficult to obtain. Various methods to reduce this effort have been proposed in the realms of active and transfer learning, but not in combination. We propose a framework for fitting new handwriting recognition models that joins active and transfer learning into a unified framework. Empirical results show the superiority of our method compared to traditional active learning, transfer learning, or standard supervised training schemes.
The Annotation Cost Of Context Switching: How Topic Models And Active Learning [May Not] Work Together, Nozomu Okuda
The Annotation Cost Of Context Switching: How Topic Models And Active Learning [May Not] Work Together, Nozomu Okuda
Theses and Dissertations
The labeling of language resources is a time consuming task, whether aided by machine learning or not. Much of the prior work in this area has focused on accelerating human annotation in the context of machine learning, yielding a variety of active learning approaches. Most of these attempt to lead an annotator to label the items which are most likely to improve the quality of an automated, machine learning-based model. These active learning approaches seek to understand the effect of item selection on the machine learning model, but give significantly less emphasis to the effect of item selection on the …
Scalable Detection And Extraction Of Data In Lists In Ocred Text For Ontology Population Using Semi-Supervised And Unsupervised Active Wrapper Induction, Thomas L. Packer
Scalable Detection And Extraction Of Data In Lists In Ocred Text For Ontology Population Using Semi-Supervised And Unsupervised Active Wrapper Induction, Thomas L. Packer
Theses and Dissertations
Lists of records in machine-printed documents contain much useful information. As one example, the thousands of family history books scanned, OCRed, and placed on-line by FamilySearch.org probably contain hundreds of millions of fact assertions about people, places, family relationships, and life events. Data like this cannot be fully utilized until a person or process locates the data in the document text, extracts it, and structures it with respect to an ontology or database schema. Yet, in the family history industry and other industries, data in lists goes largely unused because no known approach adequately addresses all of the costs, challenges, …
Practical Cost-Conscious Active Learning For Data Annotation In Annotator-Initiated Environments, Robbie A. Haertel
Practical Cost-Conscious Active Learning For Data Annotation In Annotator-Initiated Environments, Robbie A. Haertel
Theses and Dissertations
Many projects exist whose purpose is to augment raw data with annotations that increase the usefulness of the data. The number of these projects is rapidly growing and in the age of “big data” the amount of data to be annotated is likewise growing within each project. One common use of such data is in supervised machine learning, which requires labeled data to train a predictive model. Annotation is often a very expensive proposition, particularly for structured data. The purpose of this dissertation is to explore methods of reducing the cost of creating such data sets, including annotated text corpora.We …
A Bayesian Decision Theoretical Approach To Supervised Learning, Selective Sampling, And Empirical Function Optimization, James Lamond Carroll
A Bayesian Decision Theoretical Approach To Supervised Learning, Selective Sampling, And Empirical Function Optimization, James Lamond Carroll
Theses and Dissertations
Many have used the principles of statistics and Bayesian decision theory to model specific learning problems. It is less common to see models of the processes of learning in general. One exception is the model of the supervised learning process known as the "Extended Bayesian Formalism" or EBF. This model is descriptive, in that it can describe and compare learning algorithms. Thus the EBF is capable of modeling both effective and ineffective learning algorithms. We extend the EBF to model un-supervised learning, semi-supervised learning, supervised learning, and empirical function optimization. We also generalize the utility model of the EBF to …
Using Geoscience Education Graduate Students To Help Faculty Transform Teaching Practice, Teagan L. Tomlin
Using Geoscience Education Graduate Students To Help Faculty Transform Teaching Practice, Teagan L. Tomlin
Theses and Dissertations
Universities make claims about student learning that graduates don't often achieve and are under pressure to show improvement in teaching and learning in their undergraduate programs. This has been the constant focus of university-level professional development programs, but most teachers are still not using the most effective teaching methods. Individual departments need to find ways to help their instructors overcome three main challenges associated with adopting more effective student-centered teaching methods. No matter what strategy is adopted, instructors need considerable support to 1) change their beliefs about what constitutes effective teaching and learning, 2) learn to effectively implement new strategies, …