Course Outline
This course is divided into several sub-parts to address the concept of AI better. Those parts are:
1) The Pre-Requisites Session
2) Artificial Intelligence
3) Machine Learning
4) Natural Language Processing (NLP)
5) Computer Vision
6) Capstone Project
Trainers:
Avishek Das
Faculty, Dept. Of CSE, CUET.
Technical Consultant, Diligite Ltd.
Asif Iqbal Sagor
Head of R&D, Diligite Ltd.
Prerequisites Session
| No. | Topic | Session
Duration (Hour) |
Resource
Person |
| 1.
2. |
Basics of Probability and Statistics
Basic Linear Algebra |
2
2 |
|
| 3. | Basic Programming Skills | 4 |
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
2
fields
| 2. | Preparatory Classes on Python for AI & ML | |
| 3. | Data Preprocessing with Python (Lab) 2 | |
| 4. | Data Visualization with Python Library (Lab) 4 Data Visualization with Tableau (Lab) | |
| 5. |
Machine Learning
Course Outline:
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 |
Natural Language Processing (NLP)
Course Outline:
| 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 |
Computer Vision
Course Outline:
| No. | Topic Session Duration
(Hour) |
Resource
Person |
| 1. | Introduction to Computer Vision 2 Image preprocessing and augmentation (Lab) | |
| 2. | ||
| 3. | Detection and Recognition Concepts (Lab) 2 Image classification (Lab) | |
| 4. | ||
| 5. | Convolutional neural networks (Lab) 2 | |
| 6. | Deep Learning Model with TensorFlow (Lab) 2 |
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
2 Classification |
AI Tools and Libraries:
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.
Pre-requisites for this course are Probability and Statistics, Linear Algebra (basics), and Programming Knowledge (in Python).
Artificial Intelligence
Course Summary
| No. | Subject Comments |
| 1 | Course Duration 10-12 Weeks (24 Classes*) |
| 2 | Pre-requisites Yes (Probability and Statistics, Linear Algebra (basics),
Programming Knowledge (in Python). |
| 3 | Computer and Network Required
Connectivity |
| 4 | Special Device Depends on Capstone Project |
