critical point classification 1cubic activation 1global minima 1loss landscape 1polynomial activation 1shallow neural networks 1
From the 1 of 2 linked papers with an AI index.
2 papers
math.OC2026
Landscape analysis for shallow neural networks: Complete classification of critical points for cubic activation and affine target functions
Shokhrukh Ibragimov, Ilkhom Mukhammadiev, Diyora Salimova
The paper analyzes the loss landscape of shallow polynomial neural networks with monomial activations, providing criteria for the existence of global minima and a complete classifi…
cs.LG2025
Refining Diffusion Models for Motion Synthesis with an Acceleration Loss to Generate Realistic IMU Data
Lars Ole Häusler, Lena Uhlenberg, Göran Köber +2
We propose a text-to-IMU (inertial measurement unit) motion-synthesis framework to obtain realistic IMU data by fine-tuning a pretrained diffusion model with an acceleration-based…