RSS 1.0Faculty Publications-Computer Science
Browse by
Recent Submissions
-
Letting Users Choose Recommender Algorithms: An Experimental Study
(Association for Computing Machinery, 2015-09-16)Recommender systems are not one-size-fits-all; different algorithms and data sources have different strengths, making them a better or worse fit for different users and use cases. As one way of taking advantage of the ... -
Automatic Text Summarization with Neural Networks
(2004-06-22)<p>A novel technique for summarizing news articles using neural networks is presented. A neural network is trained to learn the relevant features cf sentences that should be included in the summary of the article. The ... -
-
Incremental Evolution of Trainable Neural Networks that are Backwards Compatible
(2006-02-01)<p>Supervised learning has long been used to modify the artificial neural network in order to perform classification tasks. However, the standard fully-connected layered design is often inadequate when performing such ... -
Computer Generated Holograms for Optical Neural Networks
(2001-03-01)<p>While numerous artificial neural network (ANN) models have been electronically implemented and simulated by conventional computers, optical technology provides a far superior mechanism for the implementation of large-scale ... -
Variable Hidden Layer Sizing in Elman Recurrent Neuro-Evolution
(2000-05-01)<p>The relationship between the size of the hidden layer in a neural network and performance in a particular domain is currently an open research issue. Often, the number of neurons in the hidden layer is chosen empirically ... -
Discovering Trends in Large Datasets Using Neural Networks
(2006-02-01)<p>A novel knowledge discovery technique using neural networks is presented. A neural network is trained to learn the correlations and relationships that exist in a dataset. The neural network is then pruned and modified ... -
Modified Bifurcating Neuron with Leaky-Integrate-and-Fire Model
(2004-05-11)<p>The Modified Bifurcating Neuron (MBN) is a neuron model that is capable of amplitude-to-phase conversion and volume-holographic memory. Inputs are real valued and temporally spaced. This allows information to be coded ... -
Knowledge Discovery Using Neural Networks
(2004-05-01)<p>A novel knowledge discovery technique using neural networks is presented. A neural network is trained to learn the correlations and relationships that exist in a dataset. The neural network is then pruned and modified ... -
Predicting Trends in Retinol and Beta-Carotene Plasma Levels Using Neural Networks
(2004-07-01)<p>A novel knowledge discovery and prediction technique using neural networks is presented. A neural network is trained to learn the correlations among physical and dietary characteristics of several hundred people to their ... -
Backpropagation: In Search of Performance Parameters
(2004-04-01)<p>This work is an extensive study of the backpropagation network based on a new visual tool, Equal Opportunity for Recognition (EOR) for all inputs to be recalled, which is used to evaluate the overall network performance, ... -
Text Summarization Using Neural Networks
(2004-04-01)<p>A new technique for summarizing news articles using a neural network is presented. A neural network is trained to learn the relevant characteristics of sentences that should be included in the summary of the article. ... -
Automated Natural Language Evaluators - (ANLE)
(1993-12-01)<p>By the turn of the century, it is expected that most computer applications will include a natural language processing component. Both developers and consumers of NLP systems have expressed a genuine need for standard ... -
User Perception of Differences in Recommender Algorithms
(Association for Computing Machinery, 2014-10)Recent developments in user evaluation of recommender systems have brought forth powerful new tools for understanding what makes recommendations effective and useful. We apply these methods to understand how users evaluate ...
