Back to Search
Start Over
On the Rate of Convergence of a Classifier Based on a Transformer Encoder.
- Source :
-
IEEE Transactions on Information Theory . Dec2022, Vol. 68 Issue 12, p8139-8155. 17p. - Publication Year :
- 2022
-
Abstract
- Pattern recognition based on a high-dimensional predictor is considered. A classifier is defined which is based on a Transformer encoder. The rate of convergence of the misclassification probability of the classifier towards the optimal misclassification probability is analyzed. It is shown that this classifier is able to circumvent the curse of dimensionality provided the a posteriori probability satisfies a suitable hierarchical composition model. Furthermore, the difference between the Transformer classifiers theoretically analyzed in this paper and the ones used in practice today is illustrated by means of classification problems in natural language processing. [ABSTRACT FROM AUTHOR]
- Subjects :
- *NATURAL language processing
*PATTERN recognition systems
Subjects
Details
- Language :
- English
- ISSN :
- 00189448
- Volume :
- 68
- Issue :
- 12
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Information Theory
- Publication Type :
- Academic Journal
- Accession number :
- 160651293
- Full Text :
- https://doi.org/10.1109/TIT.2022.3191747