Training the random neural network using quasi-Newton methods

DOI10.1016/S0377-2217(99)00482-8zbMath0960.90094OpenAlexW2079299054MaRDI QIDQ1584790

Aristides Likas, Andreas N. Stafylopatis

Publication date: 20 May 2001

Published in: European Journal of Operational Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0377-2217(99)00482-8

zbMATH Keywords

quasi-Newton methodsrandom neural network

Mathematics Subject Classification ID

Methods of quasi-Newton type (90C53) Deterministic network models in operations research (90B10) Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items

Modeling of throughput in production lines using response surface methodology and artificial neural networks ⋮ RANDOM NEURAL NETWORK METHODS AND DEEP LEARNING ⋮ FAST NON-NEGATIVE LEAST-SQUARES LEARNING IN THE RANDOM NEURAL NETWORK ⋮ Nonmonotone BFGS-trained recurrent neural networks for temporal sequence processing ⋮ A joint optimization of momentum item and Levenberg-Marquardt algorithm to level up the BPNN's generalization ability ⋮ Learning in the feed-forward Random Neural Network: A Critical Review ⋮ ECHO STATE QUEUEING NETWORKS: A COMBINATION OF RESERVOIR COMPUTING AND RANDOM NEURAL NETWORKS ⋮ RANDOM NEURAL NETWORK LEARNING HEURISTICS

Uses Software

• MERLIN

Cites Work

• Unnamed Item
• Unnamed Item
• MERLIN-3. 0. A multidimensional optimization environment
• Product-form queueing networks with negative and positive customers
• G-networks by triggered customer movement
• Queueing networks by negative customers and negative queue lengths
• Neural network training and simulation using a multidimensional optimization system