To operate the Blended Learning Center(BLC) at optimal level, maintenance will be performed every day at 8:30 AM and at 5:00 PM regularly which can take up to 30 minutes. Please consider scheduling your activity in the BLC platform accordingly.
Topic outline
- Artificial Intelligence Lab - Python
Artificial Intelligence Lab - Python
Instructor's Information
Name: Md. Firoz Hasan
Designation: Lecturer(Senior Scale)
email: firoz.cse@diu.edu.bd
Office address: Room#735, AB04, Level - 7
Course
Content
Introduction to Artificial Intelligence, AI
Programming Fundamentals, Search Algorithms and Optimization, Knowledge Representation
and Reasoning, Machine Learning and Data Analysis, Deep Learning and Neural
Networks, and Natural Language Processing.Course Rationale
The
Artificial Intelligence Lab is an immersive course designed to provide students
with hands-on experience in implementing and applying artificial intelligence
techniques. Through a combination of lectures, practical exercises, and project
work, students will develop a deep understanding of AI concepts and gain
proficiency in programming AI algorithms. The course focuses on both
theoretical foundations and practical implementation aspects of AI, preparing
students for real-world AI applications.
Course Objectives:
By the end of the course, students will be
able to:
·
Understand fundamental
concepts and techniques in artificial intelligence.
·
Implement and evaluate AI
algorithms and models.
·
Apply AI techniques to
solve real-world problems in various domains.
·
Analyze and interpret
data for AI applications.
·
Demonstrate proficiency
in AI programming and software tools.
·
Collaborate effectively
in a team-based AI project environment.
·
Communicate and present
AI solutions and findings clearly.
Assessment Policies:
Class Attendance | 10 |
Lab Performance | 25 |
Project | 25 |
Lab Final | 40 |
Total | 100 |
| |
Grading Policy:
Numerical Grade | Letter Grade | Grade Point |
80% and above | A+ | (A Plus) | 4.0 |
75% to less than 80% | A | (A regular) | 3.75 |
70% to less than 75% | A- | (A minus) | 3.5 |
65% to less than 70% | B+ | (B Plus) | 3.25 |
60% to less than 65% | B | (B regular) | 3.0 |
55% to less than 60% | B- | (B minus) | 2.75 |
50% to less than 55% | C+ | (C Plus) | 2.5 |
45% to less than 50% | C | C (regular) | 2.25 |
40% to less than 45% | D | | 2.0 |
Less than 40% | F | | 0.0 |
- Week 1
Week 1
Session I: Introduction to Data Visualization and Machine Learning Libraries
Aim of the Session:
– Introduce data visualization libraries
– Hands-on work for data visualization using different datasets
- Introduce Machine Learning Libraries
- Week 2
Week 2
Session II: Data Processing
Aim of the Session:
– Hands-on work with data
- Week 3
Week 3
Session III: Supervised ML Algorithms (Part 1)
Aim of this lecture:
– Discuss Linear Regression
– Discuss Logistic Regression
- Discuss KNN
– Apply Linear Regression, Logistic Regression, and KNN on Datasets
Supervised Learning Algorithm
- Week 4
Week 4
Session IV: Supervised ML Algorithms (Part 2)
Aim of this lecture:
– Discuss Linear Navie Byes
- Discuss Support Vector Machine
- Discuss Decision Tree
- Discuss Random Forest
– Apply NB, SVM, DT, and RF on Datasets
Supervised Learning Algorithm
- Week 5
Week 5
Session V: Feature Engineering and Model Optimization
Aim of the session:
- Implement different Feature Engineering techniques on Data
- Apply Optimization Techniques to improve the performance of an ML model
Feature Engineering and Model Optimization
- Week 6
Week 6
Session VI: Uninformed Search
Aim of this lecture:
– Discussion on Uninformed Search (BFS, DFS, UCS)
– Apply uninformed search on a given problem
- Week 7
Week 7
Session VII: Uninformed Search
Aim of this lecture:
– Discussion on Informed Search (Greedy, A*)
– Apply Informed search on a given problem
- Week 8
Week 8
Session VIII: Local Search and Adversial Search
Aim of the session:
- Discussion on Local Search
- Discussion Adversial search
- ApplyLocal and Adversial search - Week 9 & 10
- Week 11
Week 11
Session IX: Unsupervised Machine Learning
Aim of this session:
- Discuss Unsupervised Learning
- Implement SOTA Unsupervised algorithms
Unsupervised Learning Algorithm
- Week 12
Week 12
Session X: Artificial Neural Network
Aim of this lecture:
– Discussion on Neural Network
– Implementation of Neural Network on Datasets
- Week 13
Week 13
Session XI: Artificial Neural Network
Aim of this lecture:
– Discussion on Neural Network
– Implementation of Neural Network on Datasets
- Week 14
Week 14
Session XII: Convolutional Neural Network
Aim of this lecture:
– Discussion on Convolutional Neural Network
– Implementation of Convolutional Neural Networks on Datasets
- Week 15
Week 15
Session XIII: Recurrent Neural Network
Aim of this lecture:
– Discussion on Recurrent Neural Network
– Implementation of Recurrent Neural Networks on Datasets
- Week 16
Week 16
Project Presentation and Lab Report Submission
- Week 17