SambaNova Systems’ Post

View organization page for SambaNova Systems, graphic

46,311 followers

SambaNova researcher Etash Guha will present his paper “On the Diminishing Returns of Width for Continual Learning" at the ICLR 2024 BGPT Workshop. It shows increasing a network’s hidden dimension can decrease catastrophic forgetting but receive diminishing returns. Read his full paper here: https://lnkd.in/e5Q6YCRx. #MachineLearning #AI #UncertaintyQuantification #ConformalPrediction #ICLR2024

  • No alternative text description for this image

To view or add a comment, sign in

Explore topics