Latent Space: The AI Engineer Podcast cover image

ICLR 2024 — Best Papers & Talks (ImageGen, Vision, Transformers, State Space Models) ft. Durk Kingma, Christian Szegedy, Ilya Sutskever

Latent Space: The AI Engineer Podcast

CHAPTER

Overcoming Backpropagation Challenges in Neural Networks

This chapter explores the challenges of training neural networks that use sampling operations, particularly the issue of backpropagation through sampling nodes. It introduces the reparameterization trick as a solution to effectively optimize the training of variational autoencoders.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner