$Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete$

Training Fully Connected Neural Networks is $\exists\mathbb{R}$ -Complete

4 April 2022

Papers citing "Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete"

2 / 2 papers shown

Title
When Deep Learning Meets Polyhedral Theory: A Survey Joey Huchette Gonzalo Muñoz Thiago Serra Calvin Tsay AI4CE 84 32 0 29 Apr 2023
Benefits of depth in neural networks Matus Telgarsky 121 600 0 14 Feb 2016