Pandaemonium Architecture 6.0

In this course

Goodfellow is the originating theorist of Generative Adversarial Networks (GANs), the foundational 2014 framework that structures a generator and discriminator in adversarial competition to produce synthetic images. The course readings use GANs as a central case study in how machine learning architectures can be weaponized for both aesthetic generation and as models for understanding intelligence, particularly in works on large-scale image synthesis that build directly on Goodfellow's original formulation.

Mentioned in 1 reading

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

Appears alongside

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