2 options
Leveraging symmetric structure for improved learning in convolutional neural networks / Christine Allen-Blanchette.
- Format:
- Book
- Thesis/Dissertation
- Author/Creator:
- Allen-Blanchette, Christine, author.
- Language:
- English
- Subjects (All):
- Computer science.
- Artificial intelligence.
- Cameras.
- Principal components analysis.
- Datasets.
- Hilbert space.
- Optimization.
- Neural networks.
- Symmetry.
- Classification.
- Maps.
- Mathematical functions.
- Approximation.
- Fourier analysis.
- Learning.
- Lie groups.
- Pattern recognition.
- Robotics.
- Computer and Information Science--Penn dissertations.
- Penn dissertations--Computer and Information Science.
- Local Subjects:
- Computer science.
- Artificial intelligence.
- Cameras.
- Principal components analysis.
- Datasets.
- Hilbert space.
- Optimization.
- Neural networks.
- Symmetry.
- Classification.
- Maps.
- Mathematical functions.
- Approximation.
- Fourier analysis.
- Learning.
- Lie groups.
- Pattern recognition.
- Robotics.
- Computer and Information Science--Penn dissertations.
- Penn dissertations--Computer and Information Science.
- Genre:
- Academic theses.
- Physical Description:
- 1 online resource (98 pages)
- Contained In:
- Dissertations Abstracts International 83-02B.
- Place of Publication:
- [Philadelphia, Pennsylvania] : University of Pennsylvania ; Ann Arbor : ProQuest Dissertations & Theses, 2020.
- Language Note:
- English
- System Details:
- Mode of access: World Wide Web.
- text file
- Summary:
- The aggressive resurgence of convolutional neural network (CNN) models for prediction has led to new benchmarks in speech recognition, natural language processing and computer vision. In computer vision, the success of these models is often attributed to the combination of a highly nonlinear cascaded processing scheme and the equivariance of planar convolution to translations of the input. This thesis introduces methods that extend the equivariance capability of CNNs to linear Lie groups that describe: the motion of objects, the structure of the Euclidean world and the formation of images. The first approach introduces a framework for joint estimation of image and motion representations. The linear Lie group structure is enforced through a bilinear motion model which transforms an image representation by the linear combination of motion generators. The approach affords extrapolation of image sequences through linear extrapolation of transformation coefficients. In the second approach, 3D rotationally equivariant representations are learned by convolution of spherical functions with respect to the 3D rotation group. Methods are described for the convolution of functions on both the two- and three-spheres. The final approach enforces equivariance of representations to 2D dilated-rotations by preprocessing the input with a change of coordinates.
- Notes:
- Source: Dissertations Abstracts International, Volume: 83-02, Section: B.
- Advisors: Daniilidis, Kostas; Committee members: Gallier, Jean; Vidal, Rene; Brainard, David; Taylor, Camillo J.; Shi, Jianbo.
- Department: Computer and Information Science.
- Ph.D. University of Pennsylvania 2020.
- Local Notes:
- School code: 0175
- ISBN:
- 9798535573793
- Access Restriction:
- Restricted for use by site license.
- This item is not available from ProQuest Dissertations & Theses.
- This item must not be sold to any third party vendors.
The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.