ECE MS Thesis Defense by Haval Marsho Elias
When: Friday,
September 9, 2022
9:00 AM
-
11:00 AM
Where: Science & Engineering Building, Lester W. Cory Conference Room: Room 213A
Description: Electrical and Computer Engineering
MS Thesis Defense by Haval Marsho Elias
DATE:
September 9, 2022
TIME:
9:00 a.m.
LOCATION: Science Engineering Building, Room 213A
ZOOM: https://umassd.zoom.us/j/95793262918? pwd=OTZHcWt2eXV5Z3Aydmc1UnZZOFhuQT09
Meeting ID: 957 9326 2918
Passcode: 924612
TOPIC:
Single-Pattern Filter Algorithm for Training Analog Artificial Neural Networks
ABSTRACT:
Artificial Neural Networks (ANNs) are typically realized as computer programs designed to simulate the way in which the human brain processes information. ANNs gather their knowledge by detecting the patterns
and relationships through training not from programming. This thesis is using "Self-trained Multi-layer Analog Real-time" (SMART) architecture to solve the handwritten pattern recognition problem for numbers (0-9) by introducing a "Single-Pattern Filter Algorithm" (SPF) which takes inputs from raw data in the MNIST file for handwritten numbers (0-9) and provides 10x10 outputs to set the weights for the 10 neurons in the output layer neurons (OLNs). This thesis is also presenting MATLAB simulation using the Single-Pattern Filter algorithm.
ADVISORS:
Dr. David Rancor, Professor, Electrical and Computer Engineering, UMD
COMMITTEE MEMBERS: Dr. Dayalan Kasilingam and Dr. Paul Fortier, Electrical and Computer Engineering, UMD
Open to the public. All ECE students are encouraged to attend.
For more information, please contact Dr. David Rancor (drancour@umassd.edu, 508-999-8466).
MS Thesis Defense by Haval Marsho Elias
DATE:
September 9, 2022
TIME:
9:00 a.m.
LOCATION: Science Engineering Building, Room 213A
ZOOM: https://umassd.zoom.us/j/95793262918? pwd=OTZHcWt2eXV5Z3Aydmc1UnZZOFhuQT09
Meeting ID: 957 9326 2918
Passcode: 924612
TOPIC:
Single-Pattern Filter Algorithm for Training Analog Artificial Neural Networks
ABSTRACT:
Artificial Neural Networks (ANNs) are typically realized as computer programs designed to simulate the way in which the human brain processes information. ANNs gather their knowledge by detecting the patterns
and relationships through training not from programming. This thesis is using "Self-trained Multi-layer Analog Real-time" (SMART) architecture to solve the handwritten pattern recognition problem for numbers (0-9) by introducing a "Single-Pattern Filter Algorithm" (SPF) which takes inputs from raw data in the MNIST file for handwritten numbers (0-9) and provides 10x10 outputs to set the weights for the 10 neurons in the output layer neurons (OLNs). This thesis is also presenting MATLAB simulation using the Single-Pattern Filter algorithm.
ADVISORS:
Dr. David Rancor, Professor, Electrical and Computer Engineering, UMD
COMMITTEE MEMBERS: Dr. Dayalan Kasilingam and Dr. Paul Fortier, Electrical and Computer Engineering, UMD
Open to the public. All ECE students are encouraged to attend.
For more information, please contact Dr. David Rancor (drancour@umassd.edu, 508-999-8466).
Contact:
ECE: Electrical & Computer Engineering Department 508.999.9164 http://www.umassd.edu/engineering/ece/
Topical Areas: Faculty, General Public, Staff and Administrators, Students, Students, Graduate, Students, Undergraduate, University Community, College of Engineering, Electrical and Computer Engineering, Lectures and Seminars