machine learning roundupFriday 26 June

Self-improving recommenders and spherical CNNs

Today's ML research leans into two directions: making industrial recommenders self-improving, and adapting CNNs to the sphere for scientific data. Both papers share a focus on domain-specific architectures that automate or specialize beyond standard approaches.

In today's edition: Automated recommenders and Spherical CNNs.

Automated recommenders

Two papers tackle recommendation from different angles: one automates the algorithm iteration loop, the other enriches sparse metadata with multimodal data.

Spherical CNNs

Google's research on scalable spherical CNNs brings convolutional networks to signals on a sphere, opening up scientific applications.

research.google · 9 min

0
Scalable spherical CNNs for scientific applications

Scalable spherical CNNs address a gap in scientific ML: processing data on a sphere (e.g., climate or cosmology) without planar distortions. Google's work makes these networks practical for large-scale scientific datasets.