Chat with us on WhatsAppCall Learnizo

KTU 2024 Scheme · Semester 6 · Program Core — Artificial Intelligence and Machine Learning

Generative AI (PCCMT602) Syllabus

Official KTU 2024 Scheme syllabus for Generative AI, Semester 6, 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 6, 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

PCCMT602

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

PCCMT503 (Deep Learning Concepts)

Semester

Semester 6

Course Objective

To impart a foundational understanding of the principles behind generative AI models including GANs, VAEs and transformer-based architectures like GPT, to educate learners to apply ethical considerations for the responsible use and deployment of generative models, and to enable learners to understand the significance of prompt engineering and cost optimization in generative AI.

Module-wise Syllabus

Module 1

8 contact hours

Generative Modeling: introduction, generative vs. discriminative modeling, advances in machine learning, the rise of generative modeling, the generative modeling framework, challenges of generative modeling. Ethical considerations in generative AI, bias and fairness in generative AI systems, responsible use and deployment of generative models.

Module 2

10 contact hours

Autoencoders: the encoder, the decoder, joining the encoder to the decoder, analysis of the autoencoder, variational autoencoders; Kullback-Leibler (KL) divergence loss function. Generative Adversarial Networks: introduction to GANs, the discriminator, the generator, training the GAN, GAN challenges — oscillating loss, mode collapse, uninformative loss, hyperparameters.

Module 3

10 contact hours

Recurrent Neural Networks (RNN): architecture of RNN, Long Short-Term Memory (LSTM) and its architecture, Gated Recurrent Unit (GRU) and its architecture, encoder-decoder models, a question-answer generator using RNN and encoder-decoder; attention mechanisms, transformer architecture, self-attention, analysis of the transformer, BERT, GPT-2, Large Language Models (LLM).

Module 4

8 contact hours

Cost optimization in the development and operation of generative AI applications; fine-tuning and customizability; parameter-efficient fine-tuning methods — prompt tuning, prefix tuning, P-tuning, IA3, Low-Rank Adaptation (LoRA). Prompt engineering — clear and direct prompts, adding qualifying words for brief responses, breaking down the request; in-context learning (ICL) in LLMs.

Course Outcomes

  • CO1Explain the difference between generative and discriminative models and the need to ensure responsible use of generative models.
  • CO2Use variational autoencoders and GANs to generate new content and enhance existing data.
  • CO3Solve real-life problems using neural network based language models.
  • CO4Illustrate the significance of cost optimization and prompt engineering in generative AI applications.

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

  • Generative Deep Learning — David Foster (O'Reilly, 1st edition, 2019)
  • Deep Learning — Ian Goodfellow, Yoshua Bengio, Aaron Courville (MIT Press, 1st edition, 2016)
  • Large Language Model-Based Solutions: How to Deliver Value with Cost-Effective Generative AI Applications — Shreyas Subramanian (Wiley, 1st edition, 2024)

Reference Books

  • Deep Learning Illustrated — Jon Krohn, Grant Beyleveld, Aglaé Bassens (Pearson, 1st edition, 2020)
  • Prompt Engineering for Generative AI — James Phoenix, Mike Taylor (O'Reilly, 1st edition, 2024)
  • GANs in Action: Deep Learning with Generative Adversarial Networks — Jakub Langr, Vladimir Bok (Manning, 1st edition, 2019)

Frequently Asked Questions

How many credits is KTU Generative AI (PCCMT602)?

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 PCCMT602 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 PCCMT602?

Generative Deep Learning (David Foster); Deep Learning (Ian Goodfellow, Yoshua Bengio, Aaron Courville); Large Language Model-Based Solutions: How to Deliver Value with Cost-Effective Generative AI Applications (Shreyas Subramanian).

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

This Semester 6 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 Generative AI?

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