Course Title Fundamentals to Machine Learning
Module Title Intelligent Systems
Module Code 9 Course Code: Seng4082
CP/ECTS 5
Study Hours Lecture: 48 Laboratory: 32 Tutorial: 0 Home Study: 82
Instructor(s) Name: Mihretu Wy (MSc.) Office location: General S. B, R-3
Consultation Hours:
Course Academic Year: IV
Information
Semester: II
Course Schedule: Saturday and Sunday: 8:30 PM
Mode of Delivery: Parallel
Course Description: Machine Learning Fundamentals
This course provides a comprehensive introduction to machine learning, guiding students from
foundational concepts to practical applications. It covers key principles of machine learning,
artificial intelligence, and deep learning, offering insights into how machines learn from data and
make decisions. The course begins by exploring different types of machine learning—
supervised, unsupervised, and reinforcement learning—highlighting their respective use cases
and techniques.
Students will gain hands-on experience in Python programming, the essential language for
machine learning. The course includes tutorials on Python's basic syntax, data types, and control
structures, as well as its specialized libraries such as Numpy, Pandas, Matplotlib, Seaborn, and
Scikit-learn. These libraries are integral to data manipulation, visualization, and building
machine learning models.
A significant portion of the course is devoted to data handling and preparation, including
techniques for collecting, cleaning, and standardizing data. Students will learn how to address
missing values, scale features, and engineer new features from raw data—crucial steps for
ensuring high-performing machine learning models.
The course also introduces students to model selection, training, and optimization techniques. By
the end of the course, students will be able to evaluate and optimize machine learning models
using a variety of techniques, including hyperparameter tuning, cross-validation, and
regularization. Model evaluation metrics such as accuracy, precision, recall, and F1 score will be
explained in-depth to help students understand model performance.
By the conclusion of the course, students will have the practical skills to apply machine learning
techniques to real-world problems and the foundational knowledge to pursue more advanced
topics in machine learning and deep learning.
Key Learning Outcomes:
Understand the difference between AI, ML, and deep learning.
Gain proficiency in Python programming, including data types, functions, and loops.
Master essential Python libraries for machine learning like Numpy, Pandas, Matplotlib,
Seaborn, and Sklearn.
Learn to collect, clean, and preprocess data for machine learning.
Develop skills in feature engineering and data preparation.
Build, train, and evaluate machine learning models with real-world data.
Understand model selection, optimization, and evaluation techniques.
Course Outline
Topics Duration References
Chapter 1: Machine Learning Basics 1–2 Weeks Introduction to ML (4th Edition)
- AI vs ML vs Deep Learning
- Supervised, Unsupervised,
Reinforcement
- Deep Learning Basics
Chapter 2: Python for Machine 2–4 Weeks Python for Data Science
Learning
- Python Basics (variables, data types)
- Libraries: Numpy, Pandas
Chapter 3: Data Collection & 5–6 Weeks Data Science Handbook
Preparation
- Handling Missing Values
- Data Standardization
Chapter 4: Feature Engineering 7–8 Weeks Machine Learning Cookbook
- Encoding Categorical Variables
- Feature Selection
Chapter 5: Model Training and 9–10 Weeks Hands-On ML with Scikit-learn
Evaluation
- Selecting Algorithms
- Hyperparameter Tuning
- Model Evaluation (Precision, Recall)
Chapter 6: Unsupervised Learning 11–12 Introduction to Machine Learning (4th
Weeks Edition)
- Clustering (K-means, PCA)
Chapter 7: Neural Networks 13–14 Deep Learning with Python
Weeks
- Basics of Neural Networks
Teaching Strategy The course will be delivered in the form of lectures, demonstrations, presentations,
group discussions, and individual and group project work.
Assessment Criteria The evaluation shall be based on both formative and summative assessments which
include:
Assessment Forms % of credit allotted
Lecture (100%)
Attendance and Quiz 10
Assignments 20
Mid exam 30
Final examination 40
Practice (100%)
Lab exam 40
Project 60
