We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Curriculum learning and evolutionary optimization into deep learning for text classification.
- Authors
Elías-Miranda, Alfredo Arturo; Vallejo-Aldana, Daniel; Sánchez-Vega, Fernando; López-Monroy, A. Pastor; Rosales-Pérez, Alejandro; Muñiz-Sanchez, Victor
- Abstract
The exponential growth of social networks has given rise to a wide variety of content. Some social content violates the integrity and dignity of users, therefore, this task has become challenging. The need to deal with short texts, poorly written language, unbalanced classes, and non-thematic aspects. These can lead to overfitting in deep neural network (DNN) models used for classification tasks. Empirical evidence in previous studies indicates that some of these problems can be overcome by improving the optimization process of the DNN weights to avoid overfitting. Moreover, a well-defined learning process in the input examples could improve the order of the patterns learned throughout the optimization process. In this paper, we propose four Curriculum Learning strategies and a new Hybrid Genetic–Gradient Algorithm that proved to improve the performance of DNN models detecting the class of interest even in highly imbalanced datasets.
- Subjects
DEEP learning; ARTIFICIAL neural networks; NATURAL language processing; LEARNING; LEARNING strategies; CURRICULUM
- Publication
Neural Computing & Applications, 2023, Vol 35, Issue 28, p21129
- ISSN
0941-0643
- Publication type
Article
- DOI
10.1007/s00521-023-08632-8