Optimization Under Uncertainty Explains Empirical Success of Deep Learning Heuristics

DOI10.1007/978-3-030-66515-9_8zbMath1491.68181OpenAlexW2945104397MaRDI QIDQ5153505

O. M. Kosheleva, Vladik Ya. Kreinovich

Publication date: 30 September 2021

Published in: Black Box Optimization, Machine Learning, and No-Free Lunch Theorems (Search for Journal in Brave)

Full work available at URL: https://digitalcommons.utep.edu/cgi/viewcontent.cgi?article=2328&context=cs_techrep

zbMATH Keywords

deep learningtheoretical foundation

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Approximation methods and heuristics in mathematical programming (90C59)

Related Items (1)

Localized learning: a possible alternative to current deep learning techniques

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Applications of continuous mathematics to computer science
• Why rectified linear neurons are efficient: a possible theoretical explanation

This page was built for publication: Optimization Under Uncertainty Explains Empirical Success of Deep Learning Heuristics