Towards Lower Bounds on the Depth of ReLU Neural Networks

31 May 2021

Papers citing "Towards Lower Bounds on the Depth of ReLU Neural Networks"

9 / 9 papers shown

Title
On the Complexity of Neural Computation in Superposition Micah Adler Nir Shavit 52 2 0 05 Sep 2024
Representing Piecewise-Linear Functions by Functions with Minimal Arity Christoph Koutschan A. Ponomarchuk Josef Schicho 19 2 0 04 Jun 2024
Data Topology-Dependent Upper Bounds of Neural Network Widths Sangmin Lee Jong Chul Ye 6 0 0 25 May 2023
When Deep Learning Meets Polyhedral Theory: A Survey Joey Huchette Gonzalo Muñoz Thiago Serra Calvin Tsay AI4CE 86 32 0 29 Apr 2023
Lower Bounds on the Depth of Integral ReLU Neural Networks via Lattice Polytopes Christian Haase Christoph Hertrich Georg Loho 16 21 0 24 Feb 2023
$Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete$ Training Fully Connected Neural Networks is $\exists\mathbb{R}$ -Complete Daniel Bertschinger Christoph Hertrich Paul Jungeblut Tillmann Miltzow Simon Weber OffRL 40 30 0 04 Apr 2022
Training Thinner and Deeper Neural Networks: Jumpstart Regularization Carles Roger Riera Molina Camilo Rey Thiago Serra Eloi Puertas O. Pujol 14 4 0 30 Jan 2022
A Note on the Representation Power of GHHs Zhou Lu 13 5 0 27 Jan 2021
Benefits of depth in neural networks Matus Telgarsky 123 600 0 14 Feb 2016