IIQMC Artificial Intelligence & Machine Learning Course

### Syllabus for Artificial Intelligence & Machine Learning

#### Course Overview
This course offers a comprehensive introduction to Artificial Intelligence (AI) and Machine Learning (ML). It covers fundamental concepts, techniques, and applications, providing both theoretical knowledge and practical experience. Students will learn to develop and deploy AI and ML models, explore ethical considerations, and understand the impact of these technologies on various industries.

—

#### Week 1: Introduction to AI and ML
– **Lecture**:
– Overview of AI and ML
– Historical context and evolution
– Key milestones and current trends
– **Readings**:
– “Artificial Intelligence: A Modern Approach” by Stuart Russell and Peter Norvig (Chapter 1)
– **Assignments**:
– Research and present a landmark event in the history of AI.

—

#### Week 2: Python for AI and ML
– **Lecture**:
– Introduction to Python programming
– Essential libraries: NumPy, Pandas, Matplotlib, Scikit-learn
– **Lab**:
– Setting up the development environment
– Basic Python exercises
– **Assignments**:
– Implement a simple Python script for data manipulation.

—

#### Week 3: Supervised Learning – Regression
– **Lecture**:
– Linear and polynomial regression
– Evaluation metrics: MSE, RMSE, R² score
– **Lab**:
– Hands-on with regression models using Scikit-learn
– **Assignments**:
– Predict housing prices using a regression model.

—

#### Week 4: Supervised Learning – Classification
– **Lecture**:
– Binary and multiclass classification
– Algorithms: Logistic Regression, k-Nearest Neighbors, Decision Trees
– **Lab**:
– Building and evaluating classification models
– **Assignments**:
– Classify email spam using a classification algorithm.

—

#### Week 5: Neural Networks and Deep Learning
– **Lecture**:
– Basics of neural networks
– Deep learning concepts
– Introduction to TensorFlow and Keras
– **Lab**:
– Constructing neural networks with Keras
– **Assignments**:
– Implement a simple neural network for image recognition.

—

#### Week 6: Unsupervised Learning – Clustering
– **Lecture**:
– Clustering techniques: k-Means, Hierarchical clustering
– Evaluation metrics: Silhouette score, Davies-Bouldin Index
– **Lab**:
– Clustering datasets using Scikit-learn
– **Assignments**:
– Perform customer segmentation analysis using clustering.

—

#### Week 7: Unsupervised Learning – Dimensionality Reduction
– **Lecture**:
– PCA, t-SNE, and other dimensionality reduction techniques
– Applications and benefits
– **Lab**:
– Applying dimensionality reduction to high-dimensional datasets
– **Assignments**:
– Reduce dimensions of a dataset for visualization purposes.

—

#### Week 8: Reinforcement Learning
– **Lecture**:
– Basics of reinforcement learning
– Key concepts: Agent, Environment, Reward, Policy
– **Lab**:
– Introduction to OpenAI Gym
– Implementing simple RL algorithms
– **Assignments**:
– Train an agent to solve a basic environment in OpenAI Gym.

—

#### Week 9: Natural Language Processing (NLP)
– **Lecture**:
– Text preprocessing and representation
– NLP techniques: Sentiment Analysis, Named Entity Recognition
– **Lab**:
– Implementing NLP tasks with NLTK and SpaCy
– **Assignments**:
– Build a sentiment analysis model for movie reviews.

—

#### Week 10: Computer Vision
– **Lecture**:
– Image processing techniques
– Convolutional Neural Networks (CNNs)
– **Lab**:
– Hands-on with image classification using CNNs
– **Assignments**:
– Implement an image classifier for handwritten digit recognition.

—

#### Week 11: Advanced Topics and Trends
– **Lecture**:
– AI ethics and bias
– Recent advancements: GANs, Transfer Learning, AutoML
– **Readings**:
– Selected research papers on advanced topics
– **Assignments**:
– Research and present on a cutting-edge AI/ML technology.

—

#### Week 12: Capstone Project
– **Project**:
– Apply the concepts and techniques learned throughout the course to a real-world problem.
– Students will work in teams to identify a problem, gather and preprocess data, build and evaluate models, and present their findings.
– **Evaluation**:
– Project report and presentation

—

#### Resources
– **Textbooks**:
– “Artificial Intelligence: A Modern Approach” by Stuart Russell and Peter Norvig
– “Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow” by Aurélien Géron

– **Software**:
– Python, Jupyter Notebook
– Scikit-learn, TensorFlow, Keras, NLTK, SpaCy, OpenAI Gym

—

#### Evaluation Criteria
– **Assignments**: 40%
– **Labs**: 20%
– **Quizzes**: 10%
– **Capstone Project**: 30%

—

We look forward to embarking on this exciting journey into the world of Artificial Intelligence and Machine Learning with you!