Chat with us on WhatsAppCall Learnizo

KTU 2024 Scheme · Semester 4 · Program Elective I — Electronics and Communication Engineering

Machine Learning (PEECT413) Syllabus

Official KTU 2024 Scheme syllabus for Machine Learning, Semester 4, Program Elective I — Electronics and Communication Engineering (Electronics and Communication Engineering).

This page compiles APJ Abdul Kalam Technological University's officially published 2024 Scheme syllabus for Electronics and Communication Engineering, 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

PEECT413

Credits

3

Teaching Hours

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

CIE Marks

40

ESE Marks

60

Exam Duration

2 Hrs. 30 Min.

Prerequisites

None

Semester

Semester 4

Course Objective

To provide a comprehensive understanding of machine learning principles and techniques.

Module-wise Syllabus

Module 1

9 contact hours

Review: supervised, unsupervised machine learning techniques, dimensionality reduction techniques-PCA, SVD Instance-Based vs Model-Based Learning, Machine Learning models, Hyper parameters, regularization, Training - Batch and Online Learning, Challenges of Machine Learning: Data Issues-Quality, Relevancy, Over fitting, under fitting. Bias, variance, Performance metrics: Accuracy Recall, Precision, ROC curve

Module 2

9 contact hours

Regression: linear regression, logistic regression error functions in regression, MSE, L1, L2, Cross entropy multivariate regression. Classification: Naive Bayes classifier, Support Vector machines, Decision trees -random forests, Ensemble methods: boosting, bagging.

Module 3

7 contact hours

Unsupervised learning: Clustering-K-means, High, Hierarchical clustering, criterion functions for clustering, proximity measures, Euclidean, Manhattan, Minkowski Distances, Cosine Similarity. Reinforcement Learning: Agent based learning, Q-learning, Introduction to HMM models

Module 4

11 contact hours

Introduction to Artificial Neural Networks: Biological Neuron, Perceptron, Training, limitations, XOR problem, Multilayer perceptron, Gradient based learning, stochastic gradient descent, Activation Functions-Sigmoid, ReLU, tanh. Back propagation- Chain rule, Regularization- L1, L2,

Course Outcomes

  • CO1Analyze and apply supervised and unsupervised machine learning techniques to solve various data-driven problems.
  • CO2Develop, train, and optimize regression and classification models
  • CO3Design and execute clustering techniques, and assess their effectiveness using various proximity measures.
  • CO4Apply unsupervised learning techniques and understand reinforcement learning for complex problem-solving.

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

Textbooks & Reference Books

Textbooks

  • Hands-on Machine learning with Sc-kit Learn Keras and Tensorflow (module 1) — Aurelien Geron (Oreilly, Second edition 2019)
  • Machine learning for absolute beginners — Oliver Theobald (Second edition, —)
  • Learning Deep Learning (for module 4) — Magnus Ekman (Addison -Wesley, 2022)
  • Introduction to Machine learning with Python — Andreas C. Müller & Sarah Guido (O'Reilly, 2017)

Reference Books

  • "Pattern Recognition and Machine Learning" — . Bishop, C. M. (Springer, New York,, 2006.)
  • "Pattern Recognition". — Theodoridis, S. and Koutroumbas, K. (Academic Press, San Diego,., 2003)
  • Artificial Intelligence: a Modern Approach. — Russell, Stuart J. (:Prentice Hall,, 2010.)
  • CS229 Lecture Notes — Andrew Ng and Tengyu Ma (https://cs229.stanford. edu/main notes.pdf, 2023)

Frequently Asked Questions

How many credits is KTU Machine Learning (PEECT413)?

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 PEECT413 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, 2 Hrs. 30 Min.. Total: 100 marks.

What are the recommended textbooks for PEECT413?

Hands-on Machine learning with Sc-kit Learn Keras and Tensorflow (module 1) (Aurelien Geron); Machine learning for absolute beginners (Oliver Theobald); Learning Deep Learning (for module 4) (Magnus Ekman); Introduction to Machine learning with Python (Andreas C. Müller & Sarah Guido).

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

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

Need help with KTU Machine Learning?

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