How I Study AI - Learn AI Papers & Lectures the Easy Way

PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding

Beginner

Panagiotis Koromilas, Andreas D. Demou et al.Feb 1arXiv

PolySAE is a new kind of sparse autoencoder that keeps a simple, linear way to find features but uses a smarter decoder that can multiply features together.

#Sparse Autoencoder#Polynomial Decoder#Feature Interactions

Papers1

PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding