A neural model that implements probabilistic topics
| Autor: | Juan C. Valle-Lisboa, Álvaro Cabana, Eduardo Mizraji |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Topic model
Kronecker product Artificial neural network business.industry Computer science Cognitive Neuroscience Probabilistic logic 02 engineering and technology Machine learning computer.software_genre Computer Science Applications 03 medical and health sciences symbols.namesake Naive Bayes classifier ComputingMethodologies_PATTERNRECOGNITION 0302 clinical medicine Artificial Intelligence Kronecker delta 0202 electrical engineering electronic engineering information engineering symbols 020201 artificial intelligence & image processing Artificial intelligence business computer 030217 neurology & neurosurgery |
| Zdroj: | Neurocomputing. 171:1099-1107 |
| ISSN: | 0925-2312 |
| DOI: | 10.1016/j.neucom.2015.07.061 |
| Popis: | We present a neural network model that can execute some of the procedures used in the information sciences literature. In particular we offer a simplified notion of topic and how to implement it using neural networks that use the Kronecker tensor product. We show that the topic detecting mechanism is related to Naive Bayes statistical classifiers, and that it is able to disambiguate the meaning of polysemous words. We evaluate our network in a text categorization task, resulting in performance levels comparable to Naive Bayes classifiers, as expected. Hence, we propose a simple scalable neural model capable of dealing with machine learning tasks, while retaining biological plausibility and probabilistic transparency. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect