Avaliação de técnicas de aprendizagem de transferência em redes neurais com dados de treinamento em pequena escala

Bibliography Reference

Format:

e Milagros Jacinto e Martín Moschettoni e claudia Pons, G. P. (2023). Avaliação de técnicas de aprendizagem de transferência em redes neurais com dados de treinamento em pequena escala. Revista Eletrônica Argentina-Brasil de Tecnologias Da Informação e Da Comunicação, 1(17). https://doi.org/10.5281/zenodo.10032244

Publication Abstract

Abstract. This paper rigorously analyzes the process of building a deep neural network for image recognition and classification using Transfer Learning techniques. The biggest challenge is assuming that the training dataset is very small. The research is based on addressing a particular case study, the income of donations to the Food Bank of La Plata. The results obtained corroborate that the techniques analyzed are appropriate to solve tasks of detection and classification of images even in cases in which there is a very moderate number of samples.

BibTeX Source Entry

@article{REABTIC,
  doi = {10.5281/zenodo.10032244},
  url = {https://revistas.setrem.com.br/index.php/reabtic/article/view/451},
  issn = {2446-7634},
  note = {},
  year = {2023},
  month = {},
  pages = {},
  title = { Avaliação de técnicas de aprendizagem de transferência em redes neurais com dados de treinamento em pequena escala},
  author = {Gabriela Pérez e Milagros Jacinto e Martín Moschettoni e claudia Pons},
  number = {17},
  volume = {1},
  journal = {Revista Eletrônica Argentina-Brasil de Tecnologias da Informação e da Comunicação},
  abstract = {Abstract. This paper rigorously analyzes the process of building a deep neural network for image recognition and classification using Transfer Learning techniques. The biggest challenge is assuming that the training dataset is very small. The research is based on addressing a particular case study, the income of donations to the Food Bank of La Plata. The results obtained corroborate that the techniques analyzed are appropriate to solve tasks of detection and classification of images even in cases in which there is a very moderate number of samples.},
  keywords = {},
}