On approximate learning by multi-layered feedforward circuits

DOI10.1007/3-540-40992-0_20MaRDI QIDQ4473252zbMATH OpenFDO

Authors Barbara Hammer, Bhaskar Dasgupta

Publication date 4 August 2004

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL http://link.springer.de/link/service/series/0558/bibs/1968/19680264.htm

Mathematics Subject Classification ID

Computational difficulty of problems (lower bounds, completeness, difficulty of approximation, etc.) (68Q17) Computational learning theory (68Q32)

Recommendations

• On approximate learning by multi-layered feedforward circuits
• Hardness results for neural network approximation problems
• Training a Single Sigmoidal Neuron Is Hard
• Minimizing the quadratic training error of a sigmoid neuron is hard
• On the infeasibility of training neural networks with small mean-squared error

Cited in

(6)

• Bounds on the learning capacity of some multi-layer networks
• Scalable learning method for feedforward neural networks using minimal-enclosing-ball approximation
• On approximate learning by multi-layered feedforward circuits
• Training a Single Sigmoidal Neuron Is Hard
• An approach to encode multilayer perceptrons
• Multilevel Fine-Tuning: Closing Generalization Gaps in Approximation of Solution Maps under a Limited Budget for Training Data

This page was built for publication: On approximate learning by multi-layered feedforward circuits

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4473252)