Back to search

Cornell University

Training Paradigms For Deep Residual Networks

Abstract

dc:description.abstract

Convolutional networks are the current state of the art for image tasks. It has long been known that depth is key for increasing their expressive power, but many challenges rendered training difficult. With the advent of deep residual networks [13], the feasible depth of networks has increased from a few dozen to several hundred. Nevertheless several traditional machine learning problems persist such as overfitting, vanishing gradients, and diminishing feature reuse. Additionally, the training time for large networks is still measured in weeks. This thesis will detail two novel approaches for training deep residual networks that address the aforementioned persistent difficulties and present experimental evidence of their efficacy.

Degree

thesis:*
Name thesis:degree_name
M.S., Computer Science
Level thesis:degree_level
Master of Science
Discipline thesis:degree_discipline
Computer Science
Grantor
Cornell University
Year dc:date.issued
2016

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Sedra, Daniel
Chair dc:contributor.chair
  • Weinberger,Kilian Quirin
Committee member dc:contributor.committeemember
  • Van Loan,Charles Francis

Subjects

dc:subject × 3

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Dc Identifier Bibid
9597056

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

Sedra, Daniel. Training Paradigms For Deep Residual Networks. Master of Science thesis, Cornell University, 2016. https://hdl.handle.net/1813/44294