Pandaemonium Architecture 6.0

In this course

Ian Goodfellow is the inventor of Generative Adversarial Networks (GANs), the foundational 2014 architecture that structures training through competition between a generator and discriminator network. His original GAN formulation provides the conceptual and mathematical framework that subsequent papers in this course—particularly those on high-fidelity image synthesis—iterate upon and refine, making him essential to understanding contemporary generative AI systems that collapse the boundary between creation and discrimination.

Mentioned in 2 readings

Andrew Brock

et al., LARGE SCALE GAN TRAINING FOR HIGH FIDELITY NATURAL IMAGE SYNTHESIS

4

Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock\† Heriot-Watt University ajb5@hw.ac.uk Jeff Donahue† DeepMind jeffdonahue@google.com Karen Simonyan† DeepMind simonyan@google.com Abstract Despite recent p…A Generative Adversarial Network (GAN) involves Generator (G) and Discriminator (D) networks whose purpose, respectively, is to map random noise to samples and discriminate real and generated samples. Formally, the GAN objective, in its ori…We note that class embeddings $c$ used for the conditional BatchNorm layers in G contain a large number of weights. Instead of having a separate layer for each embedding (Miyato et al., 2018; Zhang et al., 2018), we opt to use a shared embe…

+1 more

Pandaemonium Architecture 6.0 syllabus Fall 2025

1

Additional Reading/Primary Documents: Ian J. Goodfellow, et al., Generative Adversarial Nets BJ Fogg, from Persuasive technology, using computers to change what we think and do 9. November 10 Hopeium, a hell of a drug: Cipherpunks to Finte…

Appears alongside

People mentioned in the same passages — sorted by co-occurrence weight.