Scribd
Upload
26 views2 pages

Neural Network Course Guide Book

The document is a course guidebook for 'Introduction to Neural Networks' at Bahir Dar University, detailing course information, prerequisites, objectives, and content structure. It covers fundamental methods in neural networks, including supervised and unsupervised learning paradigms, and outlines assessment types and weights. The course aims to equip students with practical skills in applying deep learning techniques and evaluating model performance.

Uploaded by

Chanyalew 21
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
26 views2 pages

Neural Network Course Guide Book

The document is a course guidebook for 'Introduction to Neural Networks' at Bahir Dar University, detailing course information, prerequisites, objectives, and content structure. It covers fundamental methods in neural networks, including supervised and unsupervised learning paradigms, and outlines assessment types and weights. The course aims to equip students with practical skills in applying deep learning techniques and evaluating model performance.

Uploaded by

Chanyalew 21
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

BAHIR DAR UNIVERSITY

BAHIR DAR INSTITUTE OF TECHNOLOGY


FACULTY OF COMPUTING
NETWORKING CHAIR UNIT
COURSE GUIDEBOOK
General information

Course Title: Introduction to Neural Networks Lecture: As per the schedule


Lab: As per the schedule
Course Code: CoSc2191 Instructor: Yonas A. Lab Assistants: TBA
Prerequisites: Instructor Address: Poly campus
Basics of probability theory, linear algebra and Office Location: Building 44 Room 107
calculus at university level. Tools (Python, Email: [email protected]
tensorflow or matlab will be used throughout the
course).
Course CP/ECTS: 6 Consultation hours: Monday 8:00 - 11:00

Target Group: Year 4th Department: Computer Science


COURSE DESCRIPTION

An introduction to fundamental methods in neural networks. Single- and multi-layer


perceptron’s; radial-basis function networks; support vector machines; stochastic machines and
deep networks; recurrent and dynamic networks; supervised and unsupervised learning;
application to pattern classification and function approximation problems.

OBJECTIVES OF THE COURSE

Upon successfully completing the course, the student will be able to:
 Understand generic machine learning terminology
 Understand motivation and functioning of the most common types of neural networks
 Understand the choices and limitations of a model for a given setting
 Apply deep learning techniques to practical problems
 Critically evaluate model performance and interpret results
 Write reports in which results are assessed and summarized in relation to aims, methods
and available data
Course Outline with Assessment & Reference
Course Content

Part I:
Introduction to neural networks:
 Introduction, motivation and history
 Components of artificial neural networks Quiz, Assignment 1, Mid
 Fundamentals on learning and training samples
 Basic neural network structure
Part II:
Supervised learning network paradigms
 The perceptron, backpropagation and its variants
 Radial basis functions
 Recurrent perceptron-like networks
Mid, Assignment 2, Final
 Hopfield networks
Part III:
Unsupervised learning network paradigms
 Self-organizing feature maps Final
 Adaptive resonance theory
Assessment
Assessment Type Weight
Quiz I and Individual Assignment 5 and 10
Mid-Exam and Group Assignment 25 and 10
Final 50
Total 100
NB: Attendance Requirement >= 85%
Course Policy: According to BiT legislations.

Reference materials

Text (required): "Neural networks and learning machines," by Simon Haykin. Pearson, 2009

Approval:
Instructor’s name and signature: Yonas Ayanaw _________

Chair holder name and signature: Kidist Meshesha ___________

You might also like