Оригинал (Original)
Автори: Павлова, М. Ц.
Заглавие: Сравнителен анализ на активационните функции в Конволюционна Невронна Мрежа
Ключови думи: Convolution Neural Network, activation functions; convolution layers; Separable Convolution layers, Keras

Абстракт: The Convolution Neural Network (CNN) which is presented in this paper is designed to use the digital images for input values. The CNN is very useful as a powerful instrument for object recognition. This paper presents a part of a research in an area of the object recognition with a CNN for recognition of forest fires. The paper will present the different activation functions used in the CNN and the aim of the paper is a comparison between all of them. There are limitations putted in the research and in this paper information on them, will be provided.

Библиография

    Издание

    TELECOM, 2020, България, София, DOI 10.1109/TELECOM50385.2020.9299559
    Autors: Pavlova, M. T.
    Title: Comparison of activation functions in convolution neural network
    Keywords: Convolution Neural Network, activation functions; convolution layers; Separable Convolution layers, Keras

    Abstract: The Convolution Neural Network (CNN) which is presented in this paper is designed to use the digital images for input values. The CNN is very useful as a powerful instrument for object recognition. This paper presents a part of a research in an area of the object recognition with a CNN for recognition of forest fires. The paper will present the different activation functions used in the CNN and the aim of the paper is a comparison between all of them. There are limitations putted in the research and in this paper information on them, will be provided.

    References

      Issue

      TELECOM, 2020, Bulgaria, Sofiq, DOI 10.1109/TELECOM50385.2020.9299559

      Цитирания (Citation/s):
      1. Ivan Trushev, Shima Schati, Dipak Patil, "On the Minimal Fire Power for Heat Detection", Information Communication and Energy Systems and Technologies (ICEST) 2021 56th International Scientific Conference on, pp. 239-242, 2021. - 2021 - в издания, индексирани в Scopus или Web of Science
      2. Florian Frankreiter, Anselm Breitenreiter, Oliver Schrape, Milos Krstic, "Power- and Area-optimized Neural Network IC-Design for Academic Education", Electronics Circuits and Systems (ICECS) 2021 28th IEEE International Conference on, pp. 1-6, 2021. - 2021 - в издания, индексирани в Scopus или Web of Science

      Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus