Reduced-order modeling of deep neural networks

DOI10.1134/S0965542521050109OpenAlexW3183892689MaRDI QIDQ2038490

Andrzej Cichocki, Julia Gusak, T. Daulbaev, E. Ponomarev, Ivan V. Oseledets

Publication date: 7 July 2021

Published in: Computational Mathematics and Mathematical Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1910.06995

zbMATH Keywords

component analysisacceleration of neural networksknowledge distillationmodel pruning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Related Items

Common structure of reduced bases for aggregation kinetics problems of varying dimensionality, New applications of matrix methods

Uses Software

• FFJORD
• torchdiffeq
• MobileNets
• FitNets

Cites Work

• Unnamed Item
• Reduced order methods for modeling and computational reduction
• Rectangular maximum-volume submatrices and their applications
• Computational Advertising: Techniques for Targeting Relevant Ads
• Nonlinear Model Reduction via Discrete Empirical Interpolation