Deep Learning: An Overview of Convolutional Neural Network(CNN)
Aziz, Irfan (2020)
2020
Laskennallisen suurten tietoaineistojen analysoinnin maisterikoulutus, FM (engl) - Master's Degree Programme in Computational Big Data Analytics
Informaatioteknologian ja viestinnän tiedekunta - Faculty of Information Technology and Communication Sciences
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Hyväksymispäivämäärä
2020-05-13
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tuni-202005135273
https://urn.fi/URN:NBN:fi:tuni-202005135273
Tiivistelmä
In the last two decades, deep learning, an area of machine learning has made exponential progress and breakthroughs. Currently, it is used in many devices and machines and is becoming more and more common in our everyday lives. This ranges from self-driving cars to real time speech translation, machine learning continues to inspire different fields of sciences. Additionally, innovation and experiments in machine learning are shared in conferences, media and workplaces.
This thesis is an overview of the progress made in traditional machine learning methods. It specifically discusses a major architecture, convolutional neural networks within deep learning, machine learning. Emphasis is given to the progress in convolutional neural networks and the different architectures such AlexNet, VGG net, ZF Net, Google Net, Microsoft Net and SENet. The application of these architectures in image classification problems is discussed in detail with comparison among different architectures.
This thesis is an overview of the progress made in traditional machine learning methods. It specifically discusses a major architecture, convolutional neural networks within deep learning, machine learning. Emphasis is given to the progress in convolutional neural networks and the different architectures such AlexNet, VGG net, ZF Net, Google Net, Microsoft Net and SENet. The application of these architectures in image classification problems is discussed in detail with comparison among different architectures.