networks through auto-generation

B-80 Ernest C. Young Hall 155 S. Grant Street West Lafayette, IN 47907-2114

of supplemental training inputs

All thesis-option graduate students at Purdue must deposit the final products of their research with the Purdue University Graduate School Thesis/Dissertation Office.

François G. Dorais, Department of Mathematics, Dartmouth College  Read more author stories on

Inclement Weather Policy for Thesis/Dissertation Workshops

Buxton [38]extends these ideas and suggests that encoded messages could be used to passmore complex information in sound and it is this type of auditory feedback thatwill be considered here.

Thesis: process X is a feasible way to do task Y

This answer to this question leads to two courses of research. If the response of a fully trained network is not improved by the introduction of new data, comparing the various auto-generation methods would be difficult. If this is found to be true, the net would be trained significantly less on the original data and then the auto-generation techniques would be applied. This technique would investigate if the total number of training iterations to shape the internal weights could be lowered when compared to fully training the network with the initial test set.

If you have trouble accessing this page because of a disability, please contact .

All of the citations here are in my .

Next Computers [175]have had high quality sound input and output facilities since they were firstbrought out and Sun Microsystems and Silicon Graphics [154,185] have both introduced workstations with similar facilities.

A. Back Propagation Neural Networks

The aim of the research described here is to provide a method to dothis.As DiGiano & Baecker [55]suggest, non-speech audio is becoming a standard feature of most new computersystems.

See how easy it is, once you know how?

It istime that sound was specifically designed into computer systems rather thanbeing an add-on or an accident of design that can be taken advantage of by theuser.

This led to ineffective uses of sound.

We have seen that users will take advantage of sounds in their computer systemsand that there is sophisticated sound hardware available currently doingnothing.

Harvey Mudd College is a member of

This thesis aims to investigate the creation of suchmultimodal interfaces.The classical uses of non-speech sound can be found in the human factorsliterature (see Deatherage [48]or McCormick & Sanders [116]).

Thesis committee selected 04/01/99

Cell phones are rapidly becoming very powerful and they provide many uses beyond just texting and talking. Look back at each week and provide examples of how some of the items you have learned are used in these devices. Please use three examples.

Thesis proposal accepted 06/04/99

A multimodal interface thatintegrated information output to both senses could capitalise on theinterdependence between them and present information in the most efficient andnatural way possible.