Імпульсні нейронні мережі для задач класифікації зображень
Loading...
Date
2021
Authors
Кравченко, Ілля
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This work is dedicated to the discussion of the main features of the classical fully-connected feed-forward Artificial Neural Network(ANN) and the Spiking Neural Network(SNN) based on their performance on the MNIST dataset and a few of its variations. Firstly, models’ architectures are discussed, then they are trained on the MNIST dataset. Finally, their performances are compared, and from the results of the experiment, the conclusion is stated.
Description
Keywords
нейронні мережі, класифікація зображень, магістерська робота