University of Jyväskylä | JYX Digital Repository

  • English  | Give feedback |
    • suomi
    • English
 
  • Login
JavaScript is disabled for your browser. Some features of this site may not work without it.
View Item 
  • JYX
  • Opinnäytteet
  • Pro gradu -tutkielmat
  • View Item
JYX > Opinnäytteet > Pro gradu -tutkielmat > View Item

The Impact of Regularization on Convolutional Neural Networks

Thumbnail
View/Open
1.3 Mb

Downloads:  
Show download detailsHide download details  
Authors
Zeeshan, Khaula
Date
2018
Discipline
TietotekniikkaMathematical Information Technology
Copyright
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.

 
Syvä oppiminen (engl. deep learning) on viime aikoina tullut suosituimmaksi koneoppimisen menetelmäksi. Konvoluutio(hermo)verkko on yksi suosituimmista syvän oppimisen arkkitehtuureista monimutkaisiin ongelmiin kuten kuvien luokitteluun, tunnistukseen ja havaitsemiseen. Syvän oppimisen menetelmien toimivuutta haittaa kuitenkin ylisovittumisongelma. Koska konvoluutioverkot ovat konenäössä tehokkaita, täytyy niiden ylisovittumisen välttämiseksi kehittää uusia menetelmiä. Tämä tutkielma tarjoaa katsauksen lähiaikoina kehitettyihin regularisointimenetelmiin konvoluutioverkkojen ja muiden syvän oppimisen menetelmien tarpeisiin. Tutkielmassa verrataan yleisimmin käytettyjä regularisointimenetelmiä (dropout, batch normalization sekä kernel -regularisointi) kouluttamalla konvoluutioverkko kuvien luokitteluun kahdelle aineistolle (CIFAR-10 ja Kagglen kissa/koira -aineisto). Mallit validoidaan 10-ositetulla ristiinvalidoinnilla. Empiiriset tulokset varmistavat, että dropout-menettely on muihin kokeiltuihin verrattuna vahva tekniikka molempien aineistojen kohdalla ...
 
Deep learning has become the most popular class of machine learning family in recent times. Convolutional neural networks is one of the most popular deep learning architecture for solving many complicated and sophisticated problems like image classification, image recognition, and image detection. However, deep learning techniques faces overfitting problems, which is a hindrance to the model performance. Since convolutional neural networks are outperforming in the field of computer vision, so the need for new regularization techniques to reduce overfitting issues in convolutional neural networks is inevitable. This thesis work provides a peek into the recently developed regularization methods particularly for convolutional neural networks and generally for other deep learning techniques. This thesis also showcases the comparison of most commonly used regularization methods (dropout, batch normalization, kernel regularization) by training convolutional neural networks for image classification on two image datasets (CIFAR-10 and Kaggle‘s Cat vs Dog). Each model is cross validated by 10- fold cross validation. Empirical results confirms that dropout is a strong regularization technique as compared to the other two methods( batch normalization and L1 and L2 regularization) on both datasets. ...
 
Keywords
artificial intelligence machine learning deep learning convolutional neural network image classification regularization k-fold cross validation dropout batch normalization kernel regularization koneoppiminen datatiede data mallit (tuotokset) analyysi data science models (objects) analysis
URI

http://urn.fi/URN:NBN:fi:jyu-201808213890

Metadata
Show full item record
Collections
  • Pro gradu -tutkielmat [24534]

Related items

Showing items with similar title or keywords.

  • Using deep neural networks for kinematic analysis : challenges and opportunities 

    Cronin, Neil J. (Elsevier BV, 2021)
    Kinematic analysis is often performed in a lab using optical cameras combined with reflective markers. With the advent of artificial intelligence techniques such as deep neural networks, it is now possible to perform such ...
  • Tree species classification of drone hyperspectral and RGB imagery with deep learning convolutional neural networks 

    Nezami, Somayeh; Khoramshahi, Ehsan; Nevalainen, Olli; Pölönen, Ilkka; Honkavaara, Eija (MDPI AG, 2020)
    Interest in drone solutions in forestry applications is growing. Using drones, datasets can be captured flexibly and at high spatial and temporal resolutions when needed. In forestry applications, fundamental tasks include ...
  • Robustness, Stability, and Fidelity of Explanations for a Deep Skin Cancer Classification Model 

    Saarela, Mirka; Geogieva, Lilia (MDPI AG, 2022)
    Skin cancer is one of the most prevalent of all cancers. Because of its being widespread and externally observable, there is a potential that machine learning models integrated into artificial intelligence systems will ...
  • Classification of Heart Sounds Using Convolutional Neural Network 

    Li, Fan; Tang, Hong; Shang, Shang; Mathiak, Klaus; Cong, Fengyu (MDPI, 2020)
    Heart sounds play an important role in the diagnosis of cardiac conditions. Due to the low signal-to-noise ratio (SNR), it is problematic and time-consuming for experts to discriminate different kinds of heart sounds. Thus, ...
  • Artificial Intelligence and Computational Science 

    Neittaanmäki, Pekka; Repin, Sergey (Springer, 2022)
    In this note, we discuss the interaction between two ways of scientific analysis. The first (classical) way is known as Mathematical Modeling (MM). It is based on a model created by humans and presented in mathematical ...
  • Browse materials
  • Browse materials
  • Articles
  • Conferences and seminars
  • Electronic books
  • Historical maps
  • Journals
  • Tunes and musical notes
  • Photographs
  • Presentations and posters
  • Publication series
  • Research reports
  • Research data
  • Study materials
  • Theses

Browse

All of JYXCollection listBy Issue DateAuthorsSubjectsPublished inDepartmentDiscipline

My Account

Login

Statistics

View Usage Statistics
  • How to publish in JYX?
  • Self-archiving
  • Publish Your Thesis Online
  • Publishing Your Dissertation
  • Publication services

Open Science at the JYU
 
Data Protection Description

Accessibility Statement

Unless otherwise specified, publicly available JYX metadata (excluding abstracts) may be freely reused under the CC0 waiver.
Open Science Centre