Abstract | ||
---|---|---|
This paper presents a non parametric compression system which makes use of the fact that a MLP has an internal representation of the data in the hidden layer. The system that we present makes a compression by using 4 or 8 times less units in the hidden layer than in the input. In order to improve the performance of the system we decided to use hints at the output of the system [3], these hints proved to be of use for improving the performance of the system. Several kind of hints were studied, and the results are compared with a system without hints. We also considered other aspects related with the implementation and learning in neural nets with a high number of weights |
Year | DOI | Venue |
---|---|---|
1997 | 10.1007/BFb0032566 | IWANN |
Keywords | Field | DocType |
non parametric coding,neural net | Data compression ratio,Compression system,Pattern recognition,Computer science,Mean squared error,Speech recognition,Coding (social sciences),Nonparametric statistics,Artificial intelligence,Artificial neural network,Machine learning | Conference |
Volume | ISSN | ISBN |
1240 | 0302-9743 | 3-540-63047-3 |
Citations | PageRank | References |
0 | 0.34 | 2 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gustavo Hernández Ábrego | 1 | 8 | 2.75 |
Enric Monte | 2 | 58 | 22.82 |
José B. Mariño | 3 | 510 | 64.66 |
GH Abrego | 4 | 0 | 0.34 |
JB Marino | 5 | 0 | 0.34 |