AI & Machine Learning With Python
About Course
Course by:
IT Business Incubator, CUET
Chattogram-4349, Bangladesh.
Course Summary
| No. | Subject | Comments |
| 1 | Course Duration | 72 Hours (24 Classes, 12 Weeks) |
| 2 | Pre-requisites | Yes (Probability and Statistics, Linear Algebra (basics), Programming Knowledge (in Python). |
| 3 | Lab Facilities | SKITBI, CUET will provide. |
| 4 | Special Device | Depends on Capstone Project. |
Schedule
Batch – 01 (Offline): Friday & Saturday 10 am to 1 pm
Batch – 02 (Online): Friday & Saturday 3 pm to 6 pm
Coordinator
Professor Dr. M. Moshiul Hoque
Professor, Dept of CSE, CUET
Director, IT Business Incubator in CUET
Former Dean, Faculty of Electrical & Computer Engineering, CUET
Chair, IEEE Bangladesh Section
Trainers
| MD. Asif Iqbal
Assessment developer, Workera.ai Head of R&D, Diligite Ltd Trainer, BDSET Project (AI & ML), BHTPA. Dipon Talukder Data & AI Specialist, Workera.ai |
Saadman Sakib
Faculty member, Dept of CSE, CUET Md. Mosharraf Hossain CEO, Diligite Ltd. Trainer, 8IT Project, BHTPA. |
Learning Outcomes
By the end of this course, participants will:
- Gain proficiency in essential AI concepts, including machine learning, NLP, and computer vision, to enhance employability.
- Develop foundational skills in probability, statistics, basic linear algebra, and programming necessary for AI applications.
- Engage in in-depth sessions covering AI fundamentals, machine learning algorithms, NLP techniques, and computer vision principles.
- Apply acquired knowledge and skills to real-world problems through a capstone project, preparing for internships and job opportunities in the AI industry.
Course Modules
This course is divided into the following six modules to address the concept of AI better.
1) The Pre-Requisites Session
2) Artificial Intelligence
3) Machine Learning
4) Natural Language Processing (NLP)
5) Computer Vision
6) Capstone Project
Module – 1: Prerequisites Session
| No. | Topic | Session Duration (Hour) | Resource Person |
| 1. | Basics of Probability and Statistics | 2 | |
| 2. | Basic Linear Algebra | 2 | |
| 3. | Basic Programming Skills | 4 |
Module – 2: Artificial Intelligence
Artificial Intelligence (AI) refers to the simulation of human intelligence processes by machines, especially computer systems. It involves the development of computer systems that can perform tasks that typically require human intelligence, such as understanding natural language, recognizing patterns, solving complex problems, learning from experience, and making decisions. AI aims to create systems that can mimic human cognitive functions and automate tasks that would normally require human intelligence.
AI is based on four fundamental concepts: Machine Learning, Deep Learning, Natural Language Processing (NLP), and Computer vision. Artificial Intelligence short courses should be focused on these subjects.
| No. | Topic | Session Duration
(Hour) |
Resource Person |
| 1. | Introduction of AI and background: What is AI? Related
fields |
2 | |
| 2. | Preparatory Classes on Python for AI & ML | 2 | |
| 3 | Data Preprocessing with Python (Lab) | 2 | |
| 4. | Data Visualization with Python Library (Lab)
Data Visualization with Tableau (Lab) |
4 | |
Module – 3: Machine Learning
Machine learning is concerned with the question of how to make computers learn from experience. The ability to learn is not only central to most aspects of intelligent behavior, but machine learning techniques have become key components of many software systems. For example, machine learning techniques are used to create spam filters, analyze customer purchase data, or detect fraud in credit card transactions. The field of Machine Learning, which addresses the challenge of producing machines that can learn, has become an extremely active, and exciting area, with an ever-expanding inventory of practical (and profitable) results, many enabled by recent advances in the underlying theory. This course will introduce the fundamental set of techniques and algorithms that constitute machine learning.
| No. | Topic | Session
Duration (Hour) |
Resource
Person |
| 1. | Introduction, Learning Paradigms | 2 | |
| 2. | Concept Learning | ||
| 3. | Bayes Classifier | 2 | |
| 4. | k-Nearest Neighbor (Lab) | ||
| 5. | Regression Model (Lab) | 2 | |
| 6. | Decision Tree (Lab) | 2 | |
| 7. | Support Vector Machines with kernels (Lab) | 2 | |
| 8. | Dimensionality Reduction (Lab) | ||
| 9. | Ensemble Learning, Boosting (Lab) | 3 | |
| 10. | Unsupervised Learning, Clustering (Lab) | 2 | |
| 11. | Classifier Evaluation (Lab) | ||
| 12 | Neural Networks, Perceptron (Lab) | 2 |
Module – 4: Natural Language Processing (NLP)
| No. | Topic | Session
Duration (Hour) |
Resource
Person |
| 1. | Fundamentals of NLP | 2 | |
| 2. | Tokenization and text preprocessing (Lab) | ||
| 3. | Language modeling (Lab) | 2 | |
| 4. | Text classification and sentiment analysis (Lab) | 2 | |
| 5. | Named entity recognition (Lab) | 2 | |
| 6. | NLP applications |
Module – 5: Computer Vision
| No. | Topic | Session Duration (Hour) | Resource
Person |
| 1. | Introduction to Computer Vision | 2 | |
| 2. | Image preprocessing and augmentation (Lab) | ||
| 3. | Detection and Recognition Concepts (Lab) | 2 | |
| 4. | Image classification (Lab) | ||
| 5. | Convolutional neural networks (Lab) | 2 | |
| 6. | Deep Learning Model with TensorFlow (Lab) | 2 |
Module – 6: Capstone Project
| No. | Topic | Session Duration (Hour) | Resource
Person |
| 1. | Breast Cancer Classification | 2 | |
| 2. | Semantic Similarity | 2 | |
| 3. | Object Detection and Recognition | 2 | |
| 4. | Binary, Multi-class and Multi-label Image Classification | 2 |
AI Tools and Libraries:
- Introduction to AI frameworks (TensorFlow, PyTorch, etc.)
- Using pre-trained models
- Hands-on programming and implementation
Book Recommendation:
1) The Hundred-Page Machine Learning Book by Andriy Burkov
2) Hands-On Computer Vision with TensorFlow 2: Leverage deep learning to create powerful image processing apps with TensorFlow 2.0 and Keras, by Benjamin Planche, Eliot Andres.
Frequently Asked Questions (FAQ)
Can I register for multiple courses?
Yes, you can register for up to two courses of your choice.
Is there an overlap in class schedules for multiple courses?
The course schedule is published in the notice section of the website.
What are the available payment methods for online enrollment?
You can pay in cash or online using the “Bkash to Bank” option.
Are evening batches available for job holders?
Yes, evening batches are available. Please visit the website’s notice board to see the routine.
Can I switch between online and offline classes?
You cannot switch between online and offline. You have to continue in one shift at a time.
How will admission be confirmed?
If you receive a confirmation email, your admission is confirmed.
Will classes be conducted in locations other than the chosen one?
No, classes will be conducted only at the chosen location.
What is the profile of the trainers?
The trainers are from the chosen faculty, along with industrial experts.
What is the deadline for enrollment?
The enrollment process will remain open until all seats are filled. There is no specific deadline, but once the capacity is reached, enrollment will close automatically.
Can I enroll physically?
To enroll physically, please visit the Multipurpose Building IT Business Incubator CUET on the third floor (rooms 301 and 302).
Will a recording of the sessions be available?
Yes, after each class, you will receive a recording, and you will have lifetime access to it
Course Content
Online Class Link (Zoom)
-
Class Link
00:00