RTMNU · Third Year B.Tech Computer Science & Engineering (Data Science) · NEP 2020
Generative AI
BDS6T23.2 · Elective III · Semester VI · 3 credits · College 30 + university 70
One of the Elective III options.
Unit 1: Introduction and Autoencoders
7 hoursAn introduction to generative AI; autoencoders, their representational power, layer size and depth; undercomplete, denoising, contractive and variational autoencoders; case study: autoencoders for dimension reduction.
Examined in the 70-mark end-semester paper
- Discriminative versus generative models
- Autoencoders and VAEs
- Denoising, sparse and contractive autoencoders
- Autoencoders and their relation to PCA
Unit 2: GANs, Autoregressive Models and Transformers
7 hoursThe structure and training of generative adversarial networks and deep convolutional GANs; autoregressive models with finite memory and long-range memory through RNNs and CNNs; transformer encoders and decoders and scaling laws; case study: a GAN-aided intrusion detection system.
Examined in the 70-mark end-semester paper
- Generative adversarial networks
- Types of GANs
- Autoregressive models with RNNs and CNNs
- Transformers and attention
- Scaling laws for language models
Unit 3: Structured Probabilistic Models
5 hoursThe problems of unstructured models; directed and undirected graphs to describe models; the partition function, separation and d-separation; converting between graphs; sampling from graphical models; case study: the restricted Boltzmann machine.
Examined in the 70-mark end-semester paper
- Directed and undirected graphical models
- Partition function and d-separation
- Sampling from graphical models
- Boltzmann machines and deep belief networks
Unit 4: Generative AI Applications
5 hoursApplications in art and creativity, image and video generation, text generation, music composition, healthcare and finance; real-world use cases and the challenges of deploying generative models.
Examined in the 70-mark end-semester paper
- Applications of generative AI
- Text-to-image and image-to-image synthesis
- Generative AI in healthcare, education and media
- Hallucination, bias and deepfakes
Unit contents are summarised from the official RTMNU syllabus . AiCanCode.org is not affiliated with Rashtrasant Tukadoji Maharaj Nagpur University (RTMNU).