IEEE Transactions on Circuits and Systems · 1989 · 286 citations · 2 references
Input Training PatternsEngineeringMachine LearningNeural Networks (Machine Learning)Computational Learning TheorySparse Neural NetworkLower BoundMathematical FoundationsNeuronal NetworkComputational ComplexityComputer ScienceNeural Networks (Computational Neuroscience)Hidden NodesDeep LearningNeural Architecture SearchRecurrent Neural NetworkNeural Scaling LawSocial Sciences
Recent results indicate that the number of hidden nodes (H) in a feedforward neural net depend only on the number of input training patterns (T). There appear to be conjectures that H is on the order of T-1 and of log/sub 2/T. A proof is given that the maximum number of separable regions (M) in the input space is a function of both H and input space dimension (d). The authors also show that H=M -1 and H=log/sub 2/M are special cases of that formulation. M defines a lower bound on T, the number of input patterns that may be used for training. Application to some experiments are investigated.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
2