GANs and Representation
Yann and Yannic discuss the computational costs of methods like GANs for image recognition, emphasizing the importance of generating points closer to the data manifold. They delve into the energy-based formulation of GANs and the built-in curriculum learning for the discriminator, shedding light on the challenges and advancements in representation learning.In this clip
From this podcast
Machine Learning Street Talk (MLST)
ICLR 2020: Yann LeCun and Energy-Based Models
Related Questions