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).
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 hoursReview: 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 hoursRegression: 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 hoursUnsupervised 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 hoursIntroduction 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)
| Attendance | 5 |
| Assignment / Microproject | 15 |
| 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.