Training thinner and deeper neural networks: jumpstart regularization

DOI10.1007/978-3-031-08011-1_23zbMath1502.68265arXiv2201.12795OpenAlexW4285164920MaRDI QIDQ2170213

Eloi Puertas, Oriol Pujol, Carles Riera, Camilo Rey, Thiago Serra

Publication date: 30 August 2022

Full work available at URL: https://arxiv.org/abs/2201.12795

zbMATH Keywords

deep learningmodel compressionReLU networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Uses Software

• Scikit
• MNIST
• TensorFlow
• Keras
• CIFAR
• PyTorch
• ImageNet
• Adam
• BERT
• AlexNet
• EfficientNet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Lossless compression of deep neural networks
• Approximation spaces of deep neural networks
• Dying ReLU and Initialization: Theory and Numerical Examples
• Learning representations by back-propagating errors
• Understanding Machine Learning
• A Stochastic Approximation Method
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Training thinner and deeper neural networks: jumpstart regularization