FREE
AKTU Foundation of Artificial and Machine Learning (BDS401) Syllabus PDF – B.Tech 2nd Year
Foundation of Artificial and Machine Learning BDS401
All syllabus, notes, question bank & PYQ for this subject
Free
Download now
- English
- Semester 4
- 0 downloads
- 0 views
Official AKTU syllabus of Foundation of Artificial and Machine Learning (BDS401) for B.Tech 2nd Year – 4 credits, L-T-P 3-1-0. Read the unit-wise course content, course outcomes, evaluation pattern and recommended books online, or download the PDF.
Syllabus — Foundation of Artificial and Machine Learning
Download PDFBDS401 · 4 credits · L-T-P 3-1-0
Course Outcomes
At the end of course, the student will be able to understand
| CO1 | Explain the fundamental concepts of Artificial Intelligence, intelligent agents, search techniques, and problem-solving strategies for AI-based applications. | K 2 |
| CO2 | Apply first-order logic, knowledge representation techniques, inference mechanisms, and ontological engineering for knowledge-based systems. | K 3 |
| CO3 | Analyze the architecture and learning process of Artificial Neural Networks, including perceptron, activation functions, and backpropagation algorithms. | K 4 |
| CO4 | Apply supervised machine learning algorithms and evaluate their performance using appropriate classification and validation metrics. | K 3 |
| CO5 | Analyze unsupervised learning techniques, clustering algorithms, and dimensionality reduction methods for discovering hidden patterns in data. | K 4 |
Course Content
| Unit | Topic | Proposed Lecture |
|---|---|---|
| I | Foundations of Artificial Intelligence What is AI? History of AI, Foundations of AI. Intelligent Agents: Rational agents, Agent architectures, Environment types. Problem Solving by Search: State-space graphs. Uninformed search strategies, Informed Search: Greedy Best-First Search, A* Search, Hill Climbing | 08 |
| II | Knowledge Representation First order logic – Knowledge Representation, Syntax and semantics in first order logic, Knowledge engineering in first order logic, Inference in First order logic. Prepositional versus first order logic, Unification and lifting, Forward chaining and Backward Chaining, Ontological Engineering. | 08 |
| III | Introduction to Artificial Neural Network Foundations: Biological neurons vs. Artificial neurons, The Perceptron model, limitations of the single-layer perceptron. Network Architecture: Multi-Layer Perceptron (MLP) and Feedforward Neural Networks. Activation Functions: Linear, Sigmoid, Tanh, Softmax, and ReLU. Training the Network-The Backpropagation algorithm, calculating gradients, Loss functions, updating weights using Gradient Descent. | 08 |
| IV | Supervised Learning Introduction to Machine learning, Learning Strategies. Classification Algorithms: Logistic Regression, K-Nearest Neighbors, Decision Trees, Support Vector Machines and Naive Bayes Classifier. Ensemble Learning: Introduction to Bagging and Boosting, Random Forests. Evaluation Metrics: Confusion Matrix, Accuracy, Precision, Recall, F1-Score, ROC-AUC Curve. | 08 |
| V | Unsupervised Learning Supervised vs. Unsupervised Learning, Clustering Algorithms, K- Means Clustering Hierarchical Clustering, DBSCAN etc., Dimensionality Reduction: The Curse of Dimensionality, Introduction to Principal Component Analysis. | 08 |
| Suggested Readings: 1. Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach, 4th Edition, Pearson, 2021. 2. Elaine Rich and Kevin Knight, Artificial Intelligence, 3rd Edition, McGraw-Hill Education. 3. Tom M. Mitchell, Machine Learning, McGraw-Hill Education, 1997. 4. Ethem Alpaydin, Introduction to Machine Learning, 4th Edition, The MIT Press, Cambridge, Massachusetts, 2020. | ||
Ratings & Reviews
No reviews yet — share your experience with this item.