Withdraw
Loading…
Practical considerations for deep learning
Paine, Thomas Le
Loading…
Permalink
https://hdl.handle.net/2142/97374
Description
- Title
- Practical considerations for deep learning
- Author(s)
- Paine, Thomas Le
- Issue Date
- 2017-04-17
- Director of Research (if dissertation) or Advisor (if thesis)
- Huang, Thomas
- Doctoral Committee Chair(s)
- Huang, Thomas
- Committee Member(s)
- Liang, Zhi-Pei
- Hoiem, Derek
- Smaragdis, Paris
- Department of Study
- Graduate College Programs
- Discipline
- Informatics
- Degree Granting Institution
- University of Illinois at Urbana-Champaign
- Degree Name
- Ph.D.
- Degree Level
- Dissertation
- Keyword(s)
- Deep learning
- Computer vision
- Abstract
- The work in this dissertation was done as a major shift in machine perception and deep learning research was happening. Neural networks have proved to be an important part of machine perception and other domains of artificial intelligence over the last several years. This is due to several advances that have made neural networks more practical for real world applications. The goal of this dissertation is to present several works that track some advances in deep learning including: the move from greedy unsupervised pre-training to end-to-end supervised learning, GPU accelerated training of large neural, and the more recent successes of auto-regressive models for generating high-dimensional data. This dissertation will present four of my works. The first, develops a novel convolutional auto-encoder, and shows it can learn useful features that improve supervised image classification results when data is scarce. The second, uses distributed systems with multiple GPUs to train neural networks. The third, develops a method for using neural networks for object detection in video. The fourth speeds up generation for auto-regressive models of time-series, i.e. Wavenet. Then I will conclude and describe some follow up research I would like to pursue including: work on speeding up generation for auto-regressive models of images, i.e. PixelCNN, and using dilated causal convolutional models for Reinforcement Learning.
- Graduation Semester
- 2017-05
- Type of Resource
- text
- Permalink
- http://hdl.handle.net/2142/97374
- Copyright and License Information
- Copyright 2017 Thomas Paine
Owning Collections
Graduate Dissertations and Theses at Illinois PRIMARY
Graduate Theses and Dissertations at IllinoisManage Files
Loading…
Edit Collection Membership
Loading…
Edit Metadata
Loading…
Edit Properties
Loading…
Embargoes
Loading…