- About
-
The Global ETD Search service is a free service for researchers
to find electronic theses and dissertations. This service is
provided by the
Networked Digital Library of Theses and Dissertations.
Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
Search results
Showing 71 to 80 of 6051 (0.1 seconds)| 71 |
Domain logic programming : theory and applications to scientific knowledge representationDryllerakis, Kostantinos January 1996 (has links)
No description available.
|
| 72 |
Voltage collapse indicators for on-line voltage security monitoring in power systemsHui, Ka Chun January 1993 (has links)
No description available.
|
| 73 |
Labelled proof theory for conditional logicLamb, Luis da Cunha January 2000 (has links)
No description available.
|
| 74 |
Neural network design using evolutionary computingTsui, Kwok Ching January 1998 (has links)
No description available.
|
| 75 |
Non-linear modelling through artificial neural networksKendall, Gary David January 1998 (has links)
No description available.
|
| 76 |
BCAP| An Artificial Neural Network Pruning Technique to Reduce OverfittingBrantley, Kiante 23 July 2016 (has links)
<p> Determining the optimal size of a neural network is complicated. Neural networks, with many free parameters, can be used to solve very complex problems. However, these neural networks are susceptible to overfitting. BCAP (Brantley-Clark Artificial Neural Network Pruning Technique) addresses overfitting by combining duplicate neurons in a neural network hidden layer, thereby forcing the network to learn more distinct features. We compare hidden units using the cosine similarity, and combine those that are similar with each other within a threshold ϵ. By doing so the co-adaption of the neurons in the network is reduced because hidden units that are highly correlated (i.e. similar) are combined. In this paper we show evidence that BCAP is successful in reducing network size while maintaining accuracy, or improving accuracy of neural networks during and after training.</p>
|
| 77 |
Knowledge-based techniques for multivariable control system designBoyle, Jean-Marc January 1987 (has links)
No description available.
|
| 78 |
Control of social reasoning in resource bounded agentsHogg, Lisa Marie Jean January 2001 (has links)
No description available.
|
| 79 |
Feedforward neural network forecasting model building evaluation : theory and application in business forecastingLiao, Kua-ping January 1999 (has links)
No description available.
|
| 80 |
Multi-agent as a decision support systemChin, Shou-fong January 1994 (has links)
No description available.
|
Page generated in 0.1238 seconds