Artificial Intelligence & Machine Learning syllabus
PCC-302-IT · Third Year Information Technology, SPPU 2024 pattern. Every unit, the marks scheme, course outcomes and books, copied from the official syllabus PDF.
Unit-wise syllabus
Introduction to Artificial Intelligence and Intelligent Agents
9 hoursDerived reading outline. Source text split at semicolons, line breaks and sentence boundaries, not an official topic hierarchy.
- Introduction to AI and AIML, History and Evolution of AI, Types of AI: (ANI, AGI, ASI),AI vs ML vs DL vs Data Science, Intelligent Agents,Agent Environment and PEAS Representation, Types of Agents: (Simple Reflex Agents, Model-Based Agents, Goal-Based Agents, Utility-Based Agents, Learning Agents), Applications of AI in Healthcare, Education, Finance, Agriculture, Industry 4.0 , Challenges and Future of AI.
- Case Study : Virtual Assistant (Chatbot), Smart Recommendation System
Preserved official unit paragraph
Introduction to AI and AIML, History and Evolution of AI, Types of AI: (ANI, AGI, ASI),AI vs ML vs DL vs Data Science, Intelligent Agents,Agent Environment and PEAS Representation, Types of Agents: (Simple Reflex Agents, Model-Based Agents, Goal-Based Agents, Utility-Based Agents, Learning Agents), Applications of AI in Healthcare, Education, Finance, Agriculture, Industry 4.0 , Challenges and Future of AI. Case Study : Virtual Assistant (Chatbot), Smart Recommendation System
Problem Solving, Search and Knowledge Representation
9 hoursDerived reading outline. Source text split at semicolons, line breaks and sentence boundaries, not an official topic hierarchy.
- Problem Formulation and State Space Representation, Search Strategies, Uninformed Search: (Breadth First Search (BFS), Depth First Search (DFS),Uniform Cost Search), Informed Search: (Heuristic Search, Greedy Best First Search, A* Search),Local Search and Hill Climbing, Knowledge Representation, Propositional Logic, Predicate Logic, Forward Chaining and Backward Chaining, Introduction to Expert Systems.
- Case Study : Route Finding using BFS, DFS and A* Search, Puzzle Solving using Search Algorithms
Preserved official unit paragraph
Problem Formulation and State Space Representation, Search Strategies, Uninformed Search: (Breadth First Search (BFS), Depth First Search (DFS),Uniform Cost Search), Informed Search: (Heuristic Search, Greedy Best First Search, A* Search),Local Search and Hill Climbing, Knowledge Representation, Propositional Logic, Predicate Logic, Forward Chaining and Backward Chaining, Introduction to Expert Systems. Case Study : Route Finding using BFS, DFS and A* Search, Puzzle Solving using Search Algorithms
Machine Learning Fundamentals and Supervised Learning
9 hoursDerived reading outline. Source text split at semicolons, line breaks and sentence boundaries, not an official topic hierarchy.
- Introduction to Machine Learning,ML Workflow and Lifecycle, Data Collection and Dataset Preparation, Data Preprocessing:(Handling Missing Values, Feature Scaling, Encoding Techniques),Training, Validation and Testing, Supervised Learning, Regression:(Linear Regression, Polynomial Regression),Classification:(Logistic Regression, Decision Tree K-Nearest Neighbors (KNN), Naïve Bayes), Model Evaluation: (Accuracy, Precision,Recall,F1-Score, Confusion Matrix) Case Study : House Price Prediction using Linear Regression, Spam Email Classification
Preserved official unit paragraph
Introduction to Machine Learning,ML Workflow and Lifecycle, Data Collection and Dataset Preparation, Data Preprocessing:(Handling Missing Values, Feature Scaling, Encoding Techniques),Training, Validation and Testing, Supervised Learning, Regression:(Linear Regression, Polynomial Regression),Classification:(Logistic Regression, Decision Tree K-Nearest Neighbors (KNN), Naïve Bayes), Model Evaluation: (Accuracy, Precision,Recall,F1-Score, Confusion Matrix) Case Study : House Price Prediction using Linear Regression, Spam Email Classification
Unsupervised Learning and Advanced Machine Learning Techniques
9 hoursDerived reading outline. Source text split at semicolons, line breaks and sentence boundaries, not an official topic hierarchy.
- Introduction to Unsupervised Learning, Clustering Fundamentals, K-Means Clustering, Hierarchical Clustering, DBSCAN, Association Rule Mining, Dimensionality Reduction, Principal Component Analysis (PCA), Feature Selection Techniques, Cluster Evaluation Metrics, Applications of Unsupervised Learning Case Study : Customer Segmentation using K-Means Clustering, Market Basket Analysis
Preserved official unit paragraph
Introduction to Unsupervised Learning, Clustering Fundamentals, K-Means Clustering, Hierarchical Clustering, DBSCAN, Association Rule Mining, Dimensionality Reduction, Principal Component Analysis (PCA), Feature Selection Techniques, Cluster Evaluation Metrics, Applications of Unsupervised Learning Case Study : Customer Segmentation using K-Means Clustering, Market Basket Analysis
Advanced Machine Learning, Model Optimization and AI Applications
9 hoursDerived reading outline. Source text split at semicolons, line breaks and sentence boundaries, not an official topic hierarchy.
- Support Vector Machines (SVM), Ensemble Learning, Bagging and Boosting, Random Forest, AdaBoost, Introduction to Reinforcement Learning, Hyperparameter Tuning, Cross Validation Techniques, Bias-Variance Tradeoff, Ethical and Responsible AI, AI Applications in Healthcare, Finance, Cybersecurity and Smart Systems.
- Case Study : Fraud Detection System, AI-based Healthcare Analytics
Preserved official unit paragraph
Support Vector Machines (SVM), Ensemble Learning, Bagging and Boosting, Random Forest, AdaBoost, Introduction to Reinforcement Learning, Hyperparameter Tuning, Cross Validation Techniques, Bias-Variance Tradeoff, Ethical and Responsible AI, AI Applications in Healthcare, Finance, Cybersecurity and Smart Systems. Case Study : Fraud Detection System, AI-based Healthcare Analytics
Marks and credits
| Head | Marks | Credit |
|---|---|---|
| CCE (continuous comprehensive evaluation) | 30 | 3 |
| End-semester exam | 70 |
Prerequisite: Programming and Problem Solving, Data Structures, Discrete Mathematics, Probability and Statistics.
Course outcomes
- CO1Analyze AI concepts, intelligent agents, and their real-world applications.
- CO2Apply search and reasoning methods for AI-based solutions.
- CO3Build and evaluate machine learning models using supervised learning techniques.
- CO4Apply unsupervised and advanced machine learning algorithms for pattern discovery and prediction.
- CO5Analyze machine learning applications, model optimization techniques and ethical implications of AI.
Books
Text books
- S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed. Hoboken, NJ: Pearson,
- 2.Stephen Marsland, Machine Learning: An Algorithmic Perspective, 2nd Edition, CRC Press.
Reference books
- Elaine Rich, Kevin Knight and Shivashankar B. Nair, Artificial Intelligence, 3rd Edition, McGraw Hill Education.
- Shalev-Shwartz S, Ben-David S. Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press; 2014.
- C. Müller and S. Guido, Machine Learning with Python, 1st ed. Sebastopol, CA: O'Reilly Media, 2016.
- E. Alpaydin, Introduction to Machine Learning, 4th ed. Cambridge, MA: MIT Press, 2020.
FAQ
How many units are in Artificial Intelligence & Machine Learning?
Artificial Intelligence & Machine Learning (PCC-302-IT) has 5 units and 45 hours of theory: Unit I Introduction to Artificial Intelligence and Intelligent Agents (9 h); Unit II Problem Solving, Search and Knowledge Representation (9 h); Unit III Machine Learning Fundamentals and Supervised Learning (9 h); Unit IV Unsupervised Learning and Advanced Machine Learning Techniques (9 h); Unit V Advanced Machine Learning, Model Optimization and AI Applications (9 h).
What is the marks scheme for Artificial Intelligence & Machine Learning?
The official Information Technology 2024 pattern syllabus lists continuous comprehensive evaluation (CCE) for 30 marks and the end-semester exam for 70 marks, for 3 credits.
What should I know before Artificial Intelligence & Machine Learning?
Prerequisite listed in the syllabus: Programming and Problem Solving, Data Structures, Discrete Mathematics, Probability and Statistics.