Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Training Methodology for a Multiplication Free Implementable Operator Based Neural Networks
Download
index.pdf
Date
2017
Author
Yıldız, Ozan
Metadata
Show full item record
Item Usage Stats
250
views
117
downloads
Cite This
Technological advances opened new possibilities for computing environments including smart phones, smart appliances, and drones. Engineers try to make these devices smart, self-sustaining through usage of machine learning techniques. However, most of the mobile environments have limited resources like memory, computing power and battery, and consequently traditional machine learning algorithms which require relatively high resources might not be suitable for them. Therefore, efficient versions of traditional machine learning algorithms receives interest for these kinds of environments. Recently, an operator named the ef-operator, which avoids multiplication is proposed as an alternative to classic vector multiplication. Recent studies, showed that ef-operator can be used on machine learning problems with small degradation on performance to gain energy efficiency. This thesis concerns with the application of this ef-operator over artificial neural networks. An artificial neural network architecture based of this ef-operator proposed which can approximate any Lebesgue integrable function. Applicability of standard backpropagation algorithm for this new network architecture is analyzed and a modified version of backpropagation algorithm with a line search step proposed for training this network architecture.
Subject Keywords
Neural networks (Computer science).
,
Artificial intelligence.
,
Machine learning.
URI
http://etd.lib.metu.edu.tr/upload/12621234/index.pdf
https://hdl.handle.net/11511/26664
Collections
Graduate School of Natural and Applied Sciences, Thesis
Suggestions
OpenMETU
Core
Deep convolutional neural networks with an application towards geospatial object recognition /
Batı, Emrecan; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2014)
The passion of human-being to invent intelligent systems becomes more and more meaningful day by day, as the data captured every second by artificial sensors needs to be examined and classified for many applications. The processing of ever-increasing amount of data by defining information explicitly seems nearly impossible, regarding the variability and the amount of the information, which reveals the need for intelligent systems that are capable of learning. Deep learning is a set of algorithms that attemp...
An Overview of Internet of Things and Wireless Communications
ULUŞAR, ÜMİT DENİZ; Al-Turjman, Fadi; Celik, Gurkan (2017-10-08)
Innovations in technology that have enabled efficient wireless tiny devices propelled the concept of Internet of Things. It is expected that mobile data traffic will experience 8-fold growth between 2015 and 2020 and the number of mobile connected devices will reach 11.6 billion by 2020. Main factors of this exponential growth and wide acceptance are the integration of several technologies and communications solutions such as wired and wireless sensor and actuator networks, next generation communication pro...
Wireless Communication Aspects in the Internet of Things: An Overview
ULUŞAR, ÜMİT DENİZ; Celik, Gurkan; Al-Turjman, Fadi (2017-10-12)
Recent advances in technology propelled the development of resource constrained tiny devices and the concept of Internet of Things (IoT). Potential applications spanning various fields of science from environmental to medical have been emerged. Different architectures, routing protocols, performance issues and goals have been suggested. In this work, we review fundamental concepts, recent developments and critical design factors under IoT-specific constraints and objectives such as energy efficiency and env...
Network Experience Scheduling and Routing Approach for Big Data Transmission in the Internet of Things
Al-Turman, Fadi; Mostarda, Leonardo; Ever, Enver; Darwish, Ahmed; Khalil, Naziha Shekh (Institute of Electrical and Electronics Engineers (IEEE), 2019-01-01)
The recent developments in the Internet of Things related technologies have caused a shift towards smart applications such as smart cities, smart homes, smart education systems, e-health, and online applications to run businesses. These, in turn, have introduced significant additional loads to the existing network infrastructures. In addition, these applications use big data and require relatively short response times. In this paper, we are introducing a new scheduling and routing approach to enhance the en...
Explainable Security in SDN-Based IoT Networks
Sarica, Alper Kaan; Angın, Pelin (2020-12-01)
The significant advances in wireless networks in the past decade have made a variety of Internet of Things (IoT) use cases possible, greatly facilitating many operations in our daily lives. IoT is only expected to grow with 5G and beyond networks, which will primarily rely on software-defined networking (SDN) and network functions virtualization for achieving the promised quality of service. The prevalence of IoT and the large attack surface that it has created calls for SDN-based intelligent security solut...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
O. Yıldız, “Training Methodology for a Multiplication Free Implementable Operator Based Neural Networks,” M.S. - Master of Science, Middle East Technical University, 2017.