Scribd
Upload
30 views4 pages

Mchine Learning Outlines

AI Slybus

Uploaded by

Muhammad Danish 307 G
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
30 views4 pages

Mchine Learning Outlines

AI Slybus

Uploaded by

Muhammad Danish 307 G
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

Lahore Garrison University

Department of Computer Sciences

PROGRAM (S) TO BE BSCS


EVALUATED
A. Course Description

Course Code CSC316


Course Title Machine Learning
Credit Hours 3
Prerequisites by No Prerequisite of the Course
Course(s) and
Topics
Assessment Midterm (25%)
Instruments with Quizzes / Assignments (15%),
Weights Class Presentation/project (10%),
(homework,
Final Exam (50%)
quizzes, midterms,
final, programming
assignments, lab
work, etc.)
Course Muhammad Sohaib
Coordinator
Textbook (or 1. Introduction to Machine Learning by Ethem Alpaydın by The MIT Press
Laboratory 2. Bishop, Christopher, Neural Networks for Pattern Recognition, Oxford
Manual for University Press, 1995
Laboratory
Courses)
Reference 1. Simon Haykin, Neural Networks: a comprehensive foundation, 2nd ed.,
Material Prentice Hall, 1999.

Additional Links

Course Goals The aim of this course is to study, learn, and understand Machine learning / Deep
learning. It enables computers to learn from examples and understand Machine
1
learning / Deep learning Deep learning techniques have been used successfully for
variety of applications, including: automatic speech recognition, image recognition,
natural language processing, age estimation, crack detection, etc.

Learning Outcomes:
Students who passed the course will be able: to understand the theory behind machine
learning methods such as regression/classification to have a grasp of the open issues and
trends in machine learning research.. The students will learn the key concepts, issues
and practices when training and modeling with machine learning architectures; as well
as have hands-on experience in using machine learning frameworks/algorithms for this
purpose.
Course Policies:
Class Attendance Mandatory., Class Participation Mandatory, Late Submission of
Assignments Not accepted. Make up for Exams and Assignments Not welcomed

2
Topics Covered in
the Course, with Basic and support material
Number of Week to be covered Homework/reports and their due
Lectures on Each dates
Topic (assume 16- (1) ● Class introduction
week instruction ● Class overview: Class
and 3 hours lecture) organization, topics
overview, software etc.
● Introduction: what is ML;
Problems, data, and tools;
Python
(2) ● Artificial Intelligence and
Machine Learning
● Concept of Self-Learning
● Basics of Machine
Learning
● Different Types of
Learning
(3) ● Data preprocessing, Quiz 1
● Feature extraction
● Dimensionality reduction
(4) ● Model selection
● Model Generalization, and
Overfitting.
● Optimization of training
Models.
(5) ● Typical Tasks in Machine Assignment 1
Learning
● Regression Vs
Classification
(6) ● Linear Regression
● Multivariate Linear
Regression
● Non-Linear Regression
(7) ● Logistic Regression Quiz 2
● Bayes’ Theorem
● Naïve Bayes Algorithm
(8) ● Decision Trees
● Nearest Neighbor
Algorithm

Midterm Examination
(10) ● Kernel Methods
● Support Vector Machines

3
(11) ● Markov Model Quiz 3
● Hidden Markov Model
(12) ● Introduction to Artificial Assignment 2
Neural Network
● Perceptron
(13) ● Fully Connected Artificial
Neural network
● Sparse Artificial Neural
Network
(14) ● Ensemble Learning
(15) ● k-Means and Hierarchical Quiz 4
Clustering.

(16) ● Self-Organizing Maps

Laboratory
Projects/Experime Already listed
nts Done in the
Course
Programming
Assignments Done Yes Research Paper at end of Semester
in the Course

You might also like