Chat with us on WhatsAppCall Learnizo

KTU 2024 Scheme · Semester 4 · Program Elective I — Artificial Intelligence and Data Science

Foundations of Pattern Recognition (PEADT415) Syllabus

Official KTU 2024 Scheme syllabus for Foundations of Pattern Recognition, Semester 4, Program Elective I — Artificial Intelligence and Data Science (Artificial Intelligence and Data Science).

This page compiles APJ Abdul Kalam Technological University's officially published 2024 Scheme syllabus for Artificial Intelligence and Data Science, Semester 4, sourced directly from KTU's official website (ktu.edu.in). Learnizo is an independent online tuition platform and is not affiliated with, endorsed by, or officially connected to APJKTU. The university may revise syllabus content after this page was last updated — always cross-check with the official KTU source for the current, authoritative version.

Course Code

PEADT415

Credits

3

Teaching Hours

3:0:0:0 (L:T:P:R)

CIE Marks

40

ESE Marks

60

Exam Duration

2Hrs. 30 Min.

Prerequisites

PCCST303

Semester

Semester 4

Course Objective

To provide a comprehensive understanding of the fundamental concepts and techniques of pattern recognition. To develop the ability to apply pattern recognition methods to solve practical problems. To enhance skills in using modern tools and techniques for feature extraction, dimensionality reduction, and machine learning algorithms

Module-wise Syllabus

Module 1

9 contact hours

Introduction to Pattern Recognition - Basics of pattern recognition, Applications and examples, Statistical pattern recognition, Introduction to classifiers: k-NN, Naive Bayes Project 1: Image Classification using k-NN and Naive Bayes - Classify images from the CIFAR-10 dataset using k-NN and Naive Bayes classifiers, and the deliverables are code implementation, project report, and presentation. Assignments: Assignment on k-NN and Naive Bayes classifiers Mini-project proposal submission

Module 2

9 contact hours

Feature Extraction and Dimensionality Reduction - Feature selection techniques, Principal Component Analysis (PCA), Non-linear dimensionality reduction methods (t-SNE, LLE) Project 2: Dimensionality Reduction for Handwritten Digit Recognition - Use PCA and LDA to reduce the dimensionality of the MNIST dataset and apply a classifier, and the deliverables are code implementation, project report, and presentation. Assignments: Assignment on PCA and LDA theory, Mid-term project: Detailed report on feature extraction project

Module 3

9 contact hours

Machine Learning Algorithms for Pattern Recognition - Support Vector Machines (SVM), Neural Networks and Deep Learning, Ensemble methods (Random Forests, Gradient Boosting), Clustering techniques (k-means, hierarchical clustering) Project 3: Text Classification using SVM and Neural Networks - Classify text documents from the 20 Newsgroups dataset using SVM and a simple neural network, and the deliverables are code implementation, project report, and presentation. Assignments: Assignment on SVM and neural network theory Group project on Ensemble methods applied to a complex dataset

Module 4

9 contact hours

Advanced Topics and Applications - Hidden Markov Models (HMM), Bayesian Networks, Pattern recognition in speech and handwriting. Project 4: Speech Recognition using Hidden Markov Models - Develop a speech recognition system using Hidden Markov Models using the dataset - TIMIT Acoustic-Phonetic Continuous Speech Corpus. The deliverables are code implementation, project report, and presentation. Tools: Python, HTK (Hidden Markov Model Toolkit). Project 5: Handwriting Recognition using Deep Learning - Develop a handwriting recognition system using deep learning techniques using the datasets - MNIST Handwritten Digits Dataset, IAM Handwriting Database. The deliverables are code implementation, project report, and presentation. Tools: Python, TensorFlow/Keras, OpenCV. Project 6: Bayesian Networks for Medical Diagnosis - Use Bayesian Networks to develop a system for medical diagnosis using the datasets - UCI Machine Learning Repository, Hepatitis Dataset. The deliverables are code implementation, project report, and presentation. Tools: Python, PyMC3, Netica. Assignments: Assignment on HMM and Bayesian networks Final project: Comprehensive pattern recognition application

Course Outcomes

  • CO1Understand and explain the fundamental concepts of pattern recognition and its applications.
  • CO2Apply statistical and machine learning techniques to solve pattern recognition problems.
  • CO3Implement feature extraction and dimensionality reduction techniques for various datasets.
  • CO4Develop and evaluate different machine learning models for pattern recognition tasks.
  • CO5Work on real-world pattern recognition projects, demonstrating problem-solving and project management skills.

Assessment Pattern (CIE: 40 marks, ESE: 60 marks)

Continuous Internal Evaluation (CIE)

Attendance5
Assignment / Microproject15
Internal Examination 1 (Written)10
Internal Examination 2 (Written)10

End Semester Examination (ESE)

Total 60 marks, 2Hrs. 30 Min.. See the official KTU syllabus document for the exact Part A / Part B question pattern for this course.

Textbooks & Reference Books

Textbooks

  • Pattern Recognition and Machine Learning — Christopher M. Bishop (Springer, 1/e, 2009)
  • Mastering Machine Learning Algorithms — Giuseppe Bonaccorso (Packt Publishing, 2/e,2020)
  • Pattern Classification — Richard Duda, Peter Hart, David Stork (Wiley, 2/e, 2007)
  • Deep Learning — Ian Goodfellow, Yoshua Bengio, and Aaron Courville (McGraw-Hill, 1/e, 1997)
  • Feature Extraction and Image Processing for Computer Vision — Mark Nixon and Alberto Aguado (Academic Press, 3/e, 2012)

Reference Books

  • The Nature of Statistical Learning Theory — Vladimir Vapnik (Springer-Verlag New York Inc., 2/e, 2010)
  • The Elements of Statistical Learning — Jerome Friedman, Robert Tibshirani, Trevor Hastie (Springer-Verlag New York Inc, 9/e, 2017)
  • Pattern Recognition — S.Theodoridis and K.Koutroumbas (Academic Press, 4/e, 2009)

Frequently Asked Questions

How many credits is KTU Foundations of Pattern Recognition (PEADT415)?

3 credits, with 3:0:0:0 (L:T:P:R) teaching hours per week, under the KTU 2024 Scheme.

How many modules are in the PEADT415 syllabus?

4 modules, 36 total contact hours.

What is the CIE and ESE mark split for this course?

CIE (Continuous Internal Evaluation): 40 marks. ESE (End Semester Examination): 60 marks, 2Hrs. 30 Min.. Total: 100 marks.

What are the recommended textbooks for PEADT415?

Pattern Recognition and Machine Learning (Christopher M. Bishop); Mastering Machine Learning Algorithms (Giuseppe Bonaccorso); Pattern Classification (Richard Duda, Peter Hart, David Stork); Deep Learning (Ian Goodfellow, Yoshua Bengio, and Aaron Courville); Feature Extraction and Image Processing for Computer Vision (Mark Nixon and Alberto Aguado).

Is this syllabus specific to one branch, or common to others too?

This Semester 4 course is listed under Program Elective I — Artificial Intelligence and Data Science at KTU under the 2024 Scheme — check the course header above for which branches it's common to.

Need help with KTU Foundations of Pattern Recognition?

Learnizo offers live, 1-on-1 online tuition for KTU AI&DS subjects — matched to your exact module and semester.