Neural networks with linear threshold activations: structure and algorithms

DOI10.1007/978-3-031-06901-7_26OpenAlexW3213639461MaRDI QIDQ2164715

Sammy Khalife, Amitabh Basu

Publication date: 16 August 2022

Full work available at URL: https://arxiv.org/abs/2111.08117

Mathematics Subject Classification ID

Computer science (68-XX)

Related Items (3)

Principled deep neural network training through linear programming ⋮ ReLU neural networks of polynomial size for exact maximum flow computation ⋮ Towards Lower Bounds on the Depth of ReLU Neural Networks

Cites Work

• Unnamed Item
• Robust trainability of single neurons
• Complexity of training ReLU neural network
• Neural Network Learning
• Approximation Algorithms for Training One-Node ReLU Neural Networks
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Neural networks with linear threshold activations: structure and algorithms