Matching Items (405)
Filtering by
- All Subjects: Choruses
Description
Machine learning models convert raw data in the form of video, images, audio,
text, etc. into feature representations that are convenient for computational process-
ing. Deep neural networks have proven to be very efficient feature extractors for a
variety of machine learning tasks. Generative models based on deep neural networks
introduce constraints on the feature space to learn transferable and disentangled rep-
resentations. Transferable feature representations help in training machine learning
models that are robust across different distributions of data. For example, with the
application of transferable features in domain adaptation, models trained on a source
distribution can be applied to a data from a target distribution even though the dis-
tributions may be different. In style transfer and image-to-image translation, disen-
tangled representations allow for the separation of style and content when translating
images.
This thesis examines learning transferable data representations in novel deep gen-
erative models. The Semi-Supervised Adversarial Translator (SAT) utilizes adversar-
ial methods and cross-domain weight sharing in a neural network to extract trans-
ferable representations. These transferable interpretations can then be decoded into
the original image or a similar image in another domain. The Explicit Disentangling
Network (EDN) utilizes generative methods to disentangle images into their core at-
tributes and then segments sets of related attributes. The EDN can separate these
attributes by controlling the ow of information using a novel combination of losses
and network architecture. This separation of attributes allows precise modi_cations
to speci_c components of the data representation, boosting the performance of ma-
chine learning tasks. The effectiveness of these models is evaluated across domain
adaptation, style transfer, and image-to-image translation tasks.
text, etc. into feature representations that are convenient for computational process-
ing. Deep neural networks have proven to be very efficient feature extractors for a
variety of machine learning tasks. Generative models based on deep neural networks
introduce constraints on the feature space to learn transferable and disentangled rep-
resentations. Transferable feature representations help in training machine learning
models that are robust across different distributions of data. For example, with the
application of transferable features in domain adaptation, models trained on a source
distribution can be applied to a data from a target distribution even though the dis-
tributions may be different. In style transfer and image-to-image translation, disen-
tangled representations allow for the separation of style and content when translating
images.
This thesis examines learning transferable data representations in novel deep gen-
erative models. The Semi-Supervised Adversarial Translator (SAT) utilizes adversar-
ial methods and cross-domain weight sharing in a neural network to extract trans-
ferable representations. These transferable interpretations can then be decoded into
the original image or a similar image in another domain. The Explicit Disentangling
Network (EDN) utilizes generative methods to disentangle images into their core at-
tributes and then segments sets of related attributes. The EDN can separate these
attributes by controlling the ow of information using a novel combination of losses
and network architecture. This separation of attributes allows precise modi_cations
to speci_c components of the data representation, boosting the performance of ma-
chine learning tasks. The effectiveness of these models is evaluated across domain
adaptation, style transfer, and image-to-image translation tasks.
ContributorsEusebio, Jose Miguel Ang (Author) / Panchanathan, Sethuraman (Thesis advisor) / Davulcu, Hasan (Committee member) / Venkateswara, Hemanth (Committee member) / Arizona State University (Publisher)
Created2018
ContributorsEvans, Bartlett R. (Conductor) / Schildkret, David (Conductor) / Glenn, Erica (Conductor) / Concert Choir (Performer) / Chamber Singers (Performer) / ASU Library. Music Library (Publisher)
Created2018-03-16
Description
The widespread adoption of computer vision models is often constrained by the issue of domain mismatch. Models that are trained with data belonging to one distribution, perform poorly when tested with data from a different distribution. Variations in vision based data can be attributed to the following reasons, viz., differences in image quality (resolution, brightness, occlusion and color), changes in camera perspective, dissimilar backgrounds and an inherent diversity of the samples themselves. Machine learning techniques like transfer learning are employed to adapt computational models across distributions. Domain adaptation is a special case of transfer learning, where knowledge from a source domain is transferred to a target domain in the form of learned models and efficient feature representations.
The dissertation outlines novel domain adaptation approaches across different feature spaces; (i) a linear Support Vector Machine model for domain alignment; (ii) a nonlinear kernel based approach that embeds domain-aligned data for enhanced classification; (iii) a hierarchical model implemented using deep learning, that estimates domain-aligned hash values for the source and target data, and (iv) a proposal for a feature selection technique to reduce cross-domain disparity. These adaptation procedures are tested and validated across a range of computer vision applications like object classification, facial expression recognition, digit recognition, and activity recognition. The dissertation also provides a unique perspective of domain adaptation literature from the point-of-view of linear, nonlinear and hierarchical feature spaces. The dissertation concludes with a discussion on the future directions for research that highlight the role of domain adaptation in an era of rapid advancements in artificial intelligence.
The dissertation outlines novel domain adaptation approaches across different feature spaces; (i) a linear Support Vector Machine model for domain alignment; (ii) a nonlinear kernel based approach that embeds domain-aligned data for enhanced classification; (iii) a hierarchical model implemented using deep learning, that estimates domain-aligned hash values for the source and target data, and (iv) a proposal for a feature selection technique to reduce cross-domain disparity. These adaptation procedures are tested and validated across a range of computer vision applications like object classification, facial expression recognition, digit recognition, and activity recognition. The dissertation also provides a unique perspective of domain adaptation literature from the point-of-view of linear, nonlinear and hierarchical feature spaces. The dissertation concludes with a discussion on the future directions for research that highlight the role of domain adaptation in an era of rapid advancements in artificial intelligence.
ContributorsDemakethepalli Venkateswara, Hemanth (Author) / Panchanathan, Sethuraman (Thesis advisor) / Li, Baoxin (Committee member) / Davulcu, Hasan (Committee member) / Ye, Jieping (Committee member) / Chakraborty, Shayok (Committee member) / Arizona State University (Publisher)
Created2017
ContributorsOwen, Ken (Conductor) / McDevitt, Mandy L. M. (Performer) / Larson, Brook (Conductor) / Wang, Lin-Yu (Performer) / Jacobs, Todd (Performer) / Morehouse, Daniel (Performer) / Magers, Kristen (Performer) / DeGrow, Gary (Performer) / DeGrow, Richard (Performer) / Women's Chorus (Performer) / Sun Devil Singers (Performer) / ASU Library. Music Library (Publisher)
Created2004-03-24
ContributorsMetz, John (Performer) / Sowers, Richard (Performer) / Collegium Musicum (Performer) / ASU Library. Music Library (Publisher)
Created1983-01-29
ContributorsEvans, Bartlett R. (Conductor) / Glenn, Erica (Conductor) / Steiner, Kieran (Conductor) / Thompson, Jason D. (Conductor) / Arizona Statesmen (Performer) / Women's Chorus (Performer) / Concert Choir (Performer) / Gospel Choir (Conductor) / ASU Library. Music Library (Publisher)
Created2019-03-15
ContributorsKillian, George W. (Performer) / Killian, Joni (Performer) / Vocal Jazz Ensemble (Performer) / ASU Library. Music Library (Publisher)
Created1992-11-05
ContributorsButler, Robb (Conductor) / McCreary, Kimilee (Conductor) / Bakko, Nicki L. (Conductor) / Schreuder, Joel (Conductor) / Larson, Matthew (Performer) / Ortman, Mory (Performer) / Graduate Chorale I (Performer) / Graduate Chorale II (Performer) / ASU Library. Music Library (Publisher)
Created1999-12-02
ContributorsGarrett, Jennifer (Conductor) / FitzPatrick, Carole (Performer) / Aspnes, Lynne (Performer) / Campbell, Andrew (Pianist) (Performer) / Ryan, Russell (Performer) / Rockmaker, Jody (Performer) / Kocour, Mike (Performer) / McLin, Katherine (Performer) / Larson, Brook Carter (Conductor) / Women's Chorus (Performer) / Men's Chorus (Performer) / ASU Library. Music Library (Publisher)
Created2009-05-04
ContributorsLarson, Brook Carter (Conductor) / Gentry, Gregory R. (Conductor) / Garrison, Ryan D. (Conductor) / Schildkret, David (Conductor) / Men's Chorus (Performer) / Symphonic Chorale (Performer) / Women's Chorus (Performer) / Chamber Singers (Performer) / Choral Union (Performer) / ASU Library. Music Library (Publisher)
Created2007-12-03