abstract: Over the last decade, deep neural networks also known as deep learning, combined with large databases and specialized hardware for computation, have made major strides in important areas such as computer vision, computational imaging and natural language processing. However, such frameworks currently suffer from some drawbacks. For example, it is generally not clear how the architectures are to be designed for different applications, or how the neural networks behave under different input perturbations and it is not easy to make the internal representations and parameters more interpretable. In this dissertation, I propose building constraints into feature maps, parameters and and design of algorithms involving neural networks for applications in low-level vision problems such as compressive imaging and multi-spectral image fusion, and high-level inference problems including activity and face recognition. Depending on the application, such constraints can be used to design architectures which are invariant/robust to certain nuisance factors, more efficient and, in some cases, more interpretable. Through extensive experiments on real-world datasets, I demonstrate these advantages of the proposed methods over conventional frameworks. / Dissertation/Thesis / Doctoral Dissertation Electrical Engineering 2019
| Identifer | oai:union.ndltd.org:asu.edu/item:55542 |
| Date | January 2019 |
| Contributors | Lohit, Suhas Anand (Author), Turaga, Pavan (Advisor), Spanias, Andreas (Committee member), Li, Baoxin (Committee member), Jayasuriya, Suren (Committee member), Arizona State University (Publisher) |
| Source Sets | Arizona State University |
| Language | English |
| Detected Language | English |
| Type | Doctoral Dissertation |
| Format | 169 pages |
| Rights | http://rightsstatements.org/vocab/InC/1.0/ |
Page generated in 0.0017 seconds