Course Objectives

 Understand foundational principles of AI and ML.
 Apply supervised and unsupervised learning algorithms.
 Explore neural networks and deep learning techniques.
 Develop hands-on skills in data preprocessing, model training, and evaluation.
 Gain exposure to NLP, computer vision, and AI ethics.

Module 1: Introduction to Artificial Intelligence

Topics

 History and Evolution of AI.
 Applications and Use Cases of AI.
 Definitions and Branches of AI.
 Intelligent Agents.
 Search Strategies (Uninformed & Informed Search).
 Game Playing.

Practicals

 Implement basic search algorithms (BFS, DFS, A*).

Module 2: Mathematical Foundations

Topics

 Linear Algebra for ML (Vectors, Matrices, Eigenvalues).
 Probability & Statistics.
 Calculus (Derivatives, Gradients).
 Optimization Techniques (Gradient Descent).

Practicals

 Linear algebra operations with NumPy.
 Probability distributions visualization.

Module 3: Machine Learning Fundamentals

Topics

 Supervised Learning Overview.
 Regression Techniques.

• - Linear Regression
• - Polynomial Regression

 Classification Techniques.

• - k-NN
• - Decision Trees
• - Naive Bayes
• - Support Vector Machines

 Unsupervised Learning.

• - Clustering (k-Means, Hierarchical)
• - Dimensionality Reduction (PCA)

 Evaluation Metrics.

Practicals

 Build regression and classification models in scikit-learn.
 Model performance evaluation.

Module 4: Feature Engineering and Data Preprocessing

Topics

 Data Cleaning & Handling Missing Values.
 Encoding Categorical Variables.
 Feature Scaling.
 Feature Selection Techniques.

Practicals

 Preprocessing pipelines for real-world datasets.

Module 5: Neural Networks and Deep Learning

Topics

 Introduction to Neural Networks.
 Activation Functions.
 Backpropagation.
 Convolutional Neural Networks (CNNs).
 Recurrent Neural Networks (RNNs).
 Transfer Learning.

Practicals

 Image classification with CNN (TensorFlow/Keras).
 Text generation with RNNs.

Module 6: Natural Language Processing

Topics

 Text Preprocessing.
 Tokenization, Stemming, Lemmatization.
 Word Embeddings (Word2Vec, GloVe).
 Sequence Models.
 Transformer Architectures.

Practicals

 Sentiment analysis on text data.
 Build a chatbot prototype.

Module 7: Reinforcement Learning

Topics

 Markov Decision Processes.
 Q-Learning.
 Policy Gradients.
 Applications in Robotics and Games.

Practicals

 Implement Q-Learning on OpenAI Gym environment.

Module 8: Model Deployment and Productionization

Topics

 Model Serving APIs.
 Model Serialization.
 Monitoring and Retraining.
 MLOps Overview.

Practicals

 Deploy ML model with Flask/FastAPI.

Module 9: Ethics and Explainability in AI

Topics

 Bias and Fairness.
 Explainable AI (XAI).
 Data Privacy Regulations.
 Responsible AI Development.

Practicals

 Fairness metrics demonstration.
 Model interpretability using SHAP.

Module 10: Capstone Project

Description

 End-to-end ML/AI solution development.
 Real-world datasets.
 Presentation and Documentation.

Examples

 Predictive maintenance.
 Image classification app.
 Chatbot with NLP.

 Python.
 scikit-learn.
 TensorFlow / PyTorch.

 Pandas.
 NumPy.

 OpenAI Gym.
 NLTK / spaCy.

Full Program

20 – 24 Weeks

Weekly Commitment

6 – 8 hours.