📚 Syllabus & Course Curriculum
Data Science & Analytics
Module-by-module breakdown of Generative AI and GANs, from foundations to a certified capstone project.
Foundations
• Explicit versus implicit density models and where GANs sit
• Latent space, sampling and the intuition behind adversarial training
• Comparing GANs, VAEs and diffusion on the axes that matter
Training
• Generator and discriminator balance and mode collapse
• Loss variants: non-saturating, Wasserstein and gradient penalty
• Spectral normalisation, regularisation and stabilisation tricks
Architectures
• DCGAN through StyleGAN and progressive growing
• Conditional generation and class or attribute control
• Image-to-image translation including paired and unpaired settings
Evaluation
• FID, IS and their known weaknesses
• Precision and recall for generative models
• Human evaluation protocols and when they are unavoidable
Use
• Data augmentation and synthetic data with utility and privacy trade-offs
• Deepfakes, consent and provenance watermarking
• Choosing diffusion over GANs in current practice, and when not to
Earn government-registered certification in Generative AI and GANs
e-Certificate and e-Marksheet issued on successful completion.
