I experimented with Hopfield networks in the context of a voice-based, query-answering system. Hopfield networks are used to store and retrieve patterns. I used this technique to store queries represented as natural language sentences and I evaluated the accuracy of the technique for error correction in a spoken question-answering dialog between a computer and a user. I show that the use of an auto-associative Hopfield network helps make the speech recognition system more fault tolerant. I also looked at the available encoding schemes to convert a natural language sentence into a pattern of zeroes and ones that can be stored in the Hopfield network reliably, and I suggest scalable data representations which allow storing a large number of queries.
| Identifer | oai:union.ndltd.org:unt.edu/info:ark/67531/metadc5551 |
| Date | 05 1900 |
| Creators | Bireddy, Chakradhar |
| Contributors | Tarau, Paul, Brazile, Robert |
| Publisher | University of North Texas |
| Source Sets | University of North Texas |
| Language | English |
| Detected Language | English |
| Type | Thesis or Dissertation |
| Format | Text |
| Rights | Use restricted to UNT Community (strictly enforced), Copyright, Bireddy, Chakradhar, Copyright is held by the author, unless otherwise noted. All rights reserved. |
Page generated in 0.0018 seconds