Chat with us on WhatsAppCall Learnizo

KTU 2024 Scheme · Semester 5 · Program Core — Artificial Intelligence and Machine Learning

Deep Learning Concepts (PCCMT503) Syllabus

Official KTU 2024 Scheme syllabus for Deep Learning Concepts, Semester 5, Program Core — Artificial Intelligence and Machine Learning (Artificial Intelligence and Machine Learning).

This page compiles APJ Abdul Kalam Technological University's officially published 2024 Scheme syllabus for Artificial Intelligence and Machine Learning, Semester 5, 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

PCCMT503

Credits

4

Teaching Hours

3:1:0:0 (L:T:P:R)

CIE Marks

40

ESE Marks

60

Exam Duration

2 Hrs 30 Min

Prerequisites

None

Semester

Semester 5

Course Objective

To give the learners an understanding of the foundations of deep learning architectures and applications, and to equip them with the skills to set up neural network architectures and use them for real-life problem solutions.

Module-wise Syllabus

Module 1

9 contact hours

Review of Neural Networks: biological neuron vs. artificial neuron, activation functions (step, sign, sigmoid, softmax, tanh, ReLU, LReLU, EReLU), single layer perceptron, linear separability, XOR problem, multilayer perceptron, back-propagation algorithm.

Module 2

11 contact hours

Convolutional Neural Networks (CNN): architectural overview, motivation, layers, filters, parameter sharing, regularization, convolution and pooling as an infinitely strong prior, variants of the convolution operation, efficient convolution computation methods, popular CNN architectures (ResNet, AlexNet, VGGNet, Inception).

Module 3

11 contact hours

Recurrent Neural Networks (RNN): model of a typical RNN, computation graph, bidirectional RNNs, encoder-decoder sequence-to-sequence architectures, BPTT for training RNNs, deep recurrent networks, recursive recurrent networks, Long Short-Term Memory networks (LSTM), Gated Recurrent Networks (GRU).

Module 4

11 contact hours

Unsupervised Deep Learning Models: autoencoders and their types (undercomplete, sparse, deep, contractive, denoising, convolutional, variational AE), Boltzmann machines and their types (Restricted Boltzmann Machines, Deep Belief Networks, Deep Boltzmann Machines). Applications of deep learning — speech processing, computer vision, natural language processing, word embedding techniques (TF-IDF, Word2Vec, GloVe).

Course Outcomes

  • CO1Illustrate fundamental neural network architectures and algorithms, including the multilayer perceptron and back-propagation.
  • CO2Design and evaluate deep learning architectures, including feed-forward networks and Convolutional Neural Networks (CNNs), and their applications in real-world problems.
  • CO3Develop and use Recurrent Neural Networks (RNNs) and LSTMs for sequence modelling and natural language processing tasks.
  • CO4Use unsupervised learning techniques such as autoencoders and Boltzmann machines to solve complex problems in computer vision and speech recognition.

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

  • Deep Learning — Ian Goodfellow, Yoshua Bengio, Aaron Courville (MIT Press, 1st edition, 2016)
  • Neural Networks and Deep Learning — Charu C. Aggarwal (Springer, 2nd edition, 2023)
  • Neural Networks and Deep Learning — Michael A. Nielsen (Determination Press, 2nd edition, 2015)
  • Learning Deep Architectures for AI (Foundations and Trends in Machine Learning) — Yoshua Bengio (now Publishers Inc., 1st edition, 2009)
  • Deep Learning: A Practitioner's Approach — Josh Patterson, Adam Gibson (O'Reilly Media, 1st edition, 2017)

Reference Books

  • Applied Deep Learning — Umberto Michelucci (Apress, 1st edition, 2018)
  • Deep Learning with Keras — Antonio Gulli, Sujit Pal (Packt Publishers, 1st edition, 2017)
  • Deep Learning with Python — Francois Chollet (Manning Publications, 1st edition, 2017)

Frequently Asked Questions

How many credits is KTU Deep Learning Concepts (PCCMT503)?

4 credits, with 3:1:0:0 (L:T:P:R) teaching hours per week, under the KTU 2024 Scheme.

How many modules are in the PCCMT503 syllabus?

4 modules, 42 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 PCCMT503?

Deep Learning (Ian Goodfellow, Yoshua Bengio, Aaron Courville); Neural Networks and Deep Learning (Charu C. Aggarwal); Neural Networks and Deep Learning (Michael A. Nielsen); Learning Deep Architectures for AI (Foundations and Trends in Machine Learning) (Yoshua Bengio); Deep Learning: A Practitioner's Approach (Josh Patterson, Adam Gibson).

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

This Semester 5 course is listed under Program Core — Artificial Intelligence and Machine Learning at KTU under the 2024 Scheme — check the course header above for which branches it's common to.

Need help with KTU Deep Learning Concepts?

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