Adaptive Second-order Derivative Approximate Greatest Descent Optimization for Deep Learning Neural Networks

Backpropagation using Stochastic Diagonal Approximate Greatest Descent (SDAGD) is a novel adaptive second-order derivative optimization method in updating weights of deep learning neural networks. SDAGD applies two-phase switching strategy to seek for solution at far using long-term optimal trajecto...

Full description

Bibliographic Details
Main Author: Tan, Hong Hui
Format: Thesis
Published: Curtin University 2019
Online Access:http://hdl.handle.net/20.500.11937/77991
_version_ 1848763926570860544
author Tan, Hong Hui
author_facet Tan, Hong Hui
author_sort Tan, Hong Hui
building Curtin Institutional Repository
collection Online Access
description Backpropagation using Stochastic Diagonal Approximate Greatest Descent (SDAGD) is a novel adaptive second-order derivative optimization method in updating weights of deep learning neural networks. SDAGD applies two-phase switching strategy to seek for solution at far using long-term optimal trajectory and automatically switch to Newton method when nearer to optimal solution. SDAGD has the advantages of steepest training roll-off rate, adaptive adjustment of step-length and the ability to deal with vanishing gradient issues in deep architecture.
first_indexed 2025-11-14T11:11:13Z
format Thesis
id curtin-20.500.11937-77991
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:11:13Z
publishDate 2019
publisher Curtin University
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-779912020-03-04T00:59:57Z Adaptive Second-order Derivative Approximate Greatest Descent Optimization for Deep Learning Neural Networks Tan, Hong Hui Backpropagation using Stochastic Diagonal Approximate Greatest Descent (SDAGD) is a novel adaptive second-order derivative optimization method in updating weights of deep learning neural networks. SDAGD applies two-phase switching strategy to seek for solution at far using long-term optimal trajectory and automatically switch to Newton method when nearer to optimal solution. SDAGD has the advantages of steepest training roll-off rate, adaptive adjustment of step-length and the ability to deal with vanishing gradient issues in deep architecture. 2019 Thesis http://hdl.handle.net/20.500.11937/77991 Curtin University fulltext
spellingShingle Tan, Hong Hui
Adaptive Second-order Derivative Approximate Greatest Descent Optimization for Deep Learning Neural Networks
title Adaptive Second-order Derivative Approximate Greatest Descent Optimization for Deep Learning Neural Networks
title_full Adaptive Second-order Derivative Approximate Greatest Descent Optimization for Deep Learning Neural Networks
title_fullStr Adaptive Second-order Derivative Approximate Greatest Descent Optimization for Deep Learning Neural Networks
title_full_unstemmed Adaptive Second-order Derivative Approximate Greatest Descent Optimization for Deep Learning Neural Networks
title_short Adaptive Second-order Derivative Approximate Greatest Descent Optimization for Deep Learning Neural Networks
title_sort adaptive second-order derivative approximate greatest descent optimization for deep learning neural networks
url http://hdl.handle.net/20.500.11937/77991