Some n-bit parity problems are solvable by feedforward networks with less than n hidden units
- 24 August 2005
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 305-308
- https://doi.org/10.1109/ijcnn.1993.713918
Abstract
No abstract availableKeywords
This publication has 11 references indexed in Scilit:
- How to solve the N-bit parity problem with two hidden unitsNeural Networks, 1992
- Optimization of the hidden unit function in feedforward neural networksNeural Networks, 1992
- A NODE PRUNING ALGORITHM FOR BACKPROPAGATION NETWORKSInternational Journal of Neural Systems, 1992
- What Size Net Gives Valid Generalization?Neural Computation, 1989
- Using Relevance to Reduce Network Size AutomaticallyConnection Science, 1989
- Dynamic Node Creation in Backpropagation NetworksConnection Science, 1989
- A Note on Minimization Algorithms which make Use of Non-quardratic Properties of the Objective FunctionIMA Journal of Applied Mathematics, 1973
- The Convergence of a Class of Double-rank Minimization AlgorithmsIMA Journal of Applied Mathematics, 1970
- A new approach to variable metric algorithmsThe Computer Journal, 1970
- Conditioning of quasi-Newton methods for function minimizationMathematics of Computation, 1970