A Penalty-Function Approach for Pruning Feedforward Neural Networks
From MaRDI portal
Publication:3123292
DOI10.1162/neco.1997.9.1.185zbMath0872.68154OpenAlexW2111719156WikidataQ52197439 ScholiaQ52197439MaRDI QIDQ3123292
Publication date: 6 March 1997
Published in: Neural Computation (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1162/neco.1997.9.1.185
Related Items (19)
Deterministic convergence analysis via smoothing group Lasso regularization and adaptive momentum for Sigma-Pi-Sigma neural network ⋮ Generating rules with predicates, terms and variables from the pruned neural networks ⋮ Neural Network Pruning with Tukey-Kramer Multiple Comparison Procedure ⋮ On Different Facets of Regularization Theory ⋮ The convergence analysis of spikeprop algorithm with smoothing \(L_{1/2}\) regularization ⋮ Greedy rule generation from discrete data and its use in neural network rule extraction ⋮ A backpropagation learning algorithm with graph regularization for feedforward neural networks ⋮ An approach to generate rules from neural networks for regression problems. ⋮ Batch gradient method with smoothing \(L_{1/2}\) regularization for training of feedforward neural networks ⋮ Specificity rule discovery in HIV-1 protease cleavage site analysis ⋮ A note on knowledge discovery using neural networks and its application to credit card screening ⋮ An evaluation of the bihyperbolic function in the optimization of the backpropagation algorithm ⋮ Feedforward Neural Network Construction Using Cross Validation ⋮ Symbolic knowledge extraction from trained neural networks: A sound approach ⋮ An alternative approach for neural network evolution with a genetic algorithm: crossover by combinatorial optimization ⋮ Convergence analyses on sparse feedforward neural networks via group lasso regularization ⋮ Extracting Rules from Neural Networks by Pruning and Hidden-Unit Splitting ⋮ Comprehensibility maximization and humanly comprehensible representations ⋮ Adaptive regularization parameter selection method for enhancing generalization capability of neural networks
Cites Work
This page was built for publication: A Penalty-Function Approach for Pruning Feedforward Neural Networks
