Biserka Petrovska

Work place: Military Academy “General Mihailo Apostolski”, University “Goce Delcev”,1000 Skopje, RMacedonia

E-mail:

Website:

Research Interests: Image Processing, Computational Learning Theory

Biography

Biserka Petrovska received BSc degree in 2002 and MSc degree in 2010, both in Faculty of electro technique and information technologies, University “St. Cyril and Methodius” Skopje. Currently, she is on Ph.D. studies in the field of image processing and deep learning. She works in Ministry of Defense of the Republic of Macedonia in Skopje and also works as Teaching Assistant at Military Academy “General Mihailo Apostolski” in Skopje, in the Department of natural and military-technical sciences

Author Articles
Classification of Small Sets of Images with Pre-trained Neural Networks

By Biserka Petrovska Igor Stojanovic Tatjana Atanasova-Pacemska

DOI: https://doi.org/10.5815/ijem.2018.04.05, Pub. Date: 8 Jul. 2018

Nowadays the rise of the artificial intelligence is with high speed. Even we are far away from the moment when machines are going to make decisions instead of human beings, the development in some fields of artificial intelligence is astonishing. Deep neural networks are such a filed. They are in a big expansion in a new millennium. Their application is wide: they are used in processing images, video, speech, audio, and text. In the last decade, researches put special attention and resources in the development of special kind of neural networks, convolutional neural networks. These networks have been widely applied to a variety of pattern recognition problems. Convolutional neural networks were trained on millions of images and it is difficult to outperform the accuracies that have been achieved. On the other hand, when we have a small dataset to train the network, there is no success to do it from a scratch. This article exploits the technique of transfer learning for classifying the images of small datasets. It consists fine-tuning of the pre-trained neural network. Here in details is presented the selection of hyper parameters in such networks, in order to maximize the classification accuracy. In the end, the directions have been proposed for the selection of the hyper parameters and of the pre-trained network which can be suitable for transfer learning.

[...] Read more.
Other Articles