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

Advancements in Self-Supervised Learning

This chapter explores key developments in data-efficient, self-supervised learning discussed at ICLR, focusing on the challenges of weak supervision. It presents a study on the impact of sampling techniques and model selection on performance in training models for autonomous vehicle imagery, revealing that strategic data selection can achieve high accuracy with significantly less data. Additionally, it introduces innovative approaches in model specification and emphasizes the role of uncertainty-based subsampling and self-supervised methods in enhancing learning outcomes.

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