Development and Comparison of Scoring Functions in Curriculum Learning


KESGİN H. T., Fatih Amasyali M.

2nd International Conference on Computing and Machine Intelligence, ICMI 2022, İstanbul, Turkey, 15 - 16 July 2022 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/icmi55296.2022.9873743
  • City: İstanbul
  • Country: Turkey
  • Keywords: Curriculum Learning, Deep Learning, Optimization
  • Yıldız Technical University Affiliated: Yes

Abstract

Curriculum Learning is the presentation of samples to the machine learning model in a meaningful order instead of a random order. The main challenge of Curriculum Learning is determining how to rank these samples. The ranking of the samples is expressed by the scoring function. In this study, scoring functions were compared using data set features, using the model to be trained, and using another model and their ensemble versions. Experiments were performed for 4 images and 4 text datasets. No significant differences were found between scoring functions for text datasets, but significant improvements were obtained in scoring functions created using transfer learning compared to classical model training and other scoring functions for image datasets. It shows that different new scoring functions are waiting to be found for text classification tasks.