Faster Training of Neural Networks for Recommender Systems
In this project we investigate the use of artificial neural networks(ANNs) as the core prediction function of a recommender system. In the past, research concerned with recommender systems that use ANNs have mainly concentrated on using collaborative-based information. We look at the effects of addi...
Main Author: | |
---|---|
Other Authors: | |
Format: | Others |
Published: |
Digital WPI
2002
|
Subjects: | |
Online Access: | https://digitalcommons.wpi.edu/etd-theses/607 https://digitalcommons.wpi.edu/cgi/viewcontent.cgi?article=1606&context=etd-theses |
id |
ndltd-wpi.edu-oai-digitalcommons.wpi.edu-etd-theses-1606 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-wpi.edu-oai-digitalcommons.wpi.edu-etd-theses-16062019-03-22T05:46:17Z Faster Training of Neural Networks for Recommender Systems Kogel, Wendy E. In this project we investigate the use of artificial neural networks(ANNs) as the core prediction function of a recommender system. In the past, research concerned with recommender systems that use ANNs have mainly concentrated on using collaborative-based information. We look at the effects of adding content-based information and how altering the topology of the network itself affects the accuracy of the recommendations generated. In particular, we investigate a mixture of experts topology. We create two expert clusters in the hidden layer of the ANN, one for content-based data and another for collaborative-based data. This greatly reduces the number of connections between the input and hidden layers. Our experimental evaluation shows that this new architecture produces the same accuracy of recommendation as the fully connected configuration with a large decrease in the amount of time it takes to train the network. This decrease in time is a great advantage because of the need for recommender systems to provide real time results to the user. 2002-05-01T07:00:00Z text application/pdf https://digitalcommons.wpi.edu/etd-theses/607 https://digitalcommons.wpi.edu/cgi/viewcontent.cgi?article=1606&context=etd-theses Masters Theses (All Theses, All Years) Digital WPI Sergio A. Alvarez, Advisor Micha Hofri, Department Head Lee A. Becker, Reader Carolina Ruiz, Advisor mixture of experts recommender systems neural networks |
collection |
NDLTD |
format |
Others
|
sources |
NDLTD |
topic |
mixture of experts recommender systems neural networks |
spellingShingle |
mixture of experts recommender systems neural networks Kogel, Wendy E. Faster Training of Neural Networks for Recommender Systems |
description |
In this project we investigate the use of artificial neural networks(ANNs) as the core prediction function of a recommender system. In the past, research concerned with recommender systems that use ANNs have mainly concentrated on using collaborative-based information. We look at the effects of adding content-based information and how altering the topology of the network itself affects the accuracy of the recommendations generated. In particular, we investigate a mixture of experts topology. We create two expert clusters in the hidden layer of the ANN, one for content-based data and another for collaborative-based data. This greatly reduces the number of connections between the input and hidden layers. Our experimental evaluation shows that this new architecture produces the same accuracy of recommendation as the fully connected configuration with a large decrease in the amount of time it takes to train the network. This decrease in time is a great advantage because of the need for recommender systems to provide real time results to the user. |
author2 |
Sergio A. Alvarez, Advisor |
author_facet |
Sergio A. Alvarez, Advisor Kogel, Wendy E. |
author |
Kogel, Wendy E. |
author_sort |
Kogel, Wendy E. |
title |
Faster Training of Neural Networks for Recommender Systems |
title_short |
Faster Training of Neural Networks for Recommender Systems |
title_full |
Faster Training of Neural Networks for Recommender Systems |
title_fullStr |
Faster Training of Neural Networks for Recommender Systems |
title_full_unstemmed |
Faster Training of Neural Networks for Recommender Systems |
title_sort |
faster training of neural networks for recommender systems |
publisher |
Digital WPI |
publishDate |
2002 |
url |
https://digitalcommons.wpi.edu/etd-theses/607 https://digitalcommons.wpi.edu/cgi/viewcontent.cgi?article=1606&context=etd-theses |
work_keys_str_mv |
AT kogelwendye fastertrainingofneuralnetworksforrecommendersystems |
_version_ |
1719005761922662400 |