FAST NON-NEGATIVE LEAST-SQUARES LEARNING IN THE RANDOM NEURAL NETWORK

DOI10.1017/S0269964816000061zbMath1373.62478MaRDI QIDQ5358086

Stelios Timotheou

Publication date: 19 September 2017

Published in: Probability in the Engineering and Informational Sciences (Search for Journal in Brave)

zbMATH Keywords

random neural networknon-negative least squares supervised learningquasi-Newton solution algorithm

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Quadratic programming (90C20) Neural networks for/in biological studies, artificial life and related topics (92B20) Neural nets and related approaches to inference from stochastic processes (62M45)

Cites Work

• Trends in extreme learning machines: a review
• Training multilayer neural networks using fast global learning algorithm -- least-squares and penalized optimization methods
• \(G\)-networks: A unifying model for neural and queueing networks
• Representations of quasi-Newton matrices and their use in limited memory methods
• \(G\)-networks: A versatile approach for work removal in queueing networks
• Training the random neural network using quasi-Newton methods
• Random Neural Networks with Synchronized Interactions
• Projected gradient methods for linearly constrained problems
• Product-form queueing networks with negative and positive customers
• Numerical Optimization
• G-networks by triggered customer movement
• On computational aspects of bounded linear least squares problems
• A Global Optimum Approach for One-Layer Neural Networks
• Extensions and Applications of the Householder Algorithm for Solving Linear Least Squares Problems
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: FAST NON-NEGATIVE LEAST-SQUARES LEARNING IN THE RANDOM NEURAL NETWORK