Back to search

Cornell University

Training and Understanding Deep Neural Networks for Robotics, Design, and Visual Perception

Abstract

dc:description.abstract

Over the last decade, researchers have made significant progress toward training and understanding larger and more powerful deep neural networks. This thesis contains several contributions toward this effort. The first chapter gives a brief introduction. The next two chapters describe applications and extensions of existing techniques to specific problems. First we consider the task of creating gaits for legged robots and describe the performance of various learning algorithms for automating generation of quadruped gaits. Notably, labels employed for learning are gather entirely for real-world experiments run in the learning loop. This results in a challenging learning scenario with limited labels, but through the use of models with the appropriate assumptions, gaits are found that are nine times faster than those designed by hand. In the next chapter, we discuss the task of enabling easier design of three dimensional (3D) shapes via machine learning. We describe the front end presentation and back end algorithms that enabled non-expert users to generate millions of shapes online. The remaining chapters describe approaches to understand network training and behavior. The first details several visualizations useful for training Restricted Boltzmann Machines (RBMs) and an application to a synthetic 3D data set. The second investigates a basic property of trained neural networks: to what extent parameters learned on one task can be transferred to another task. The third discusses the Deep Visualization Toolbox, open source software written to aid in understanding individual neurons in the middle of a large neural network. An additional chapter is supplied in the appendix as the author of this thesis and another researcher contributed equally to it. In this final section, the local vs. distributed nature of neural network representations is studied experimentally.

Degree

thesis:*
Name thesis:degree_name
Ph. D., Computer Science
Level thesis:degree_level
Doctor of Philosophy
Discipline thesis:degree_discipline
Computer Science
Grantor
Cornell University
Year dc:date.issued
2018

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Yosinski, Jason
Chair dc:contributor.chair
  • Lipson, Hod
Committee members dc:contributor.committeemember
  • Sirer, Emin G.
  • Edelman, Shimon J.
  • Clune, Jeffrey M.
  • Bengio, Yoshua

Subjects

dc:subject × 7

Rights

dc:rights
Statement dc:rights
  • Attribution-NonCommercial 4.0 International
Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Dc Identifier Bibid
10489764
Dc Identifier Other
ProQuest Submission ID: 10929
ProQuest Publication ID: 10839724

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Yosinski, Jason. Training and Understanding Deep Neural Networks for Robotics, Design, and Visual Perception. Doctor of Philosophy thesis, Cornell University, 2018. https://hdl.handle.net/1813/59668