Open AccessComparative analysis of accuracy of various neural networks and optimization algorithms in recognition of clothing items task
Author(s) -
Nikita Andriyanov
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1661/1/012017
Subject(s) - mnist database , artificial neural network , gradient descent , computer science , task (project management) , optimization algorithm , artificial intelligence , set (abstract data type) , pattern recognition (psychology) , algorithm , data set , optimization problem , machine learning , data mining , mathematics , mathematical optimization , engineering , systems engineering , programming language
The study conducted the investigation of the accuracy of neural networks trained with various parameters of the neural network model for the standard MNIST data set containing 70,000 images of clothing items belonging to 10 classes. In particular, the influence of the number of neurons and the number of layers on the recognition accuracy was studied, and dependences on indicators such as the number of training epochs and the optimization algorithm were obtained. In addition, a brief overview of existing solutions was performed to select optimization algorithms. According to the research results, it was found that the best estimates on the database used were provided by the ADAM optimization algorithm with the largest number of training epochs and the most complex network structure. At the same time, the least accuracy was provided by the optimization method based on simple gradient descent. Best results were obtained for a multi-layer network with ADAM optimization and k-fold cross-validation.