Browsing PhD Dissertations - DO NOT EDIT by Author "Manry, Michael T."
Now showing items 1-6 of 6
-
AFFINE INVARIANCE IN MULTILAYER PERCEPTRON TRAINING
Nguyen, Son Nam; 0000-0001-9409-4738 (2019-08-06)Training methods for both shallow and deep neural nets are dominated by first order algorithms related to back propagation and conjugate gradient. However, these methods lack affine invariance so performance is damaged by ... -
Automated multistep classifier sizing and training for deep learner
Tyagi, Kanishka; 0000-0002-6104-1645 (2018-08-13)Training algorithms for deep learning have recently been proposed with notable success, beating the start-of-the-art in certain areas like audio, speech and language processing. The key role is played by learning multiple ... -
A Family Of Robust Second Order Training Algorithms
Malalur, Sanjeev Sreenivasa Rao (Electrical Engineering, 2009-08)Starting with the concept of equivalent networks, a framework for analyzing the effect of linear dependence on training of a multi-layer perceptron is established. Detailed mathematical analyses are carried out to show ... -
Feature Selection Using an Extended Piecewise Linear Orthonormal Floating Search
Rawat, Rohit; 0000-0002-2039-2713 (2016-12-20)The piecewise linear orthonormal floating search (PLOFS) is a wrapper method for feature selection that uses a piecewise linear network (PLN) to evaluate candidate subsets. PLOFS has difficulty working on high dimensional ... -
Multistep Second Order Training For The Multilayer Perceptron
Robinson, Melvin Deloyd (Electrical Engineering, 2013-07-22)Training a feedforward multilayer perceptron (MLP) requires obtaining train- ing data and solving a non-convex optimization problem to calculate the network's weights. Various problems can arise during training that ... -
Sequences Of Near-optimal Feedforward Neural Networks
Lakshmi Narasimha, Pramod (Electrical Engineering, 2007-09-17)In order to facilitate complexity optimization in feedforward networks, several integrated growing and pruning algorithms are developed. First, a growing scheme is reviewed which iteratively adds new hidden units to ...