Optimal Brain Damage
Explore this paper's citation graph
Summary
A class of practical and nearly optimal schemes for adapting the size of a neural network by using second-derivative information to make a tradeoff between network complexity and training set error is derived.
- Type
- article
- Published
- 1989-01-01
- Cited by
- 5,404
- References
- 17
- OpenAlex
- https://openalex.org/W2114766824
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:7785881
Keywords
Computer science, Generalization, Artificial neural network, Class (philosophy), Artificial intelligence
References
- Modeles connexionnistes de l'apprentissage
- Large Automatic Learning, Rule Extraction, and Generalization
- Generalization and network design strategies
- Inductive principles of the search for empirical dependences (methods based on weak convergence of probability measures)
- A Back-Propagation Algorithm with Optimal Use of Hidden Units
- Use of statistical models for time series analysis
- Comparing Biases for Minimal Network Construction with Back-Propagation
- Skeletonization: A Technique for Trimming the Fat from a Network via Relevance Assessment
- Backpropagation Applied to Handwritten Zip Code Recognition
- Handwritten Digit Recognition with a Back-Propagation Network
- What Size Net Gives Valid Generalization?
- Consonant recognition by modular construction of large phonemic time-delay neural networks
- PhD thesis: Modeles connexionnistes de l'apprentissage (connectionist learning models)
- Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities
Cited by
- Looking for a new AI paradigm: Evolving connectionist and fuzzy connectionist systems—Theory and applications for adaptive, on-line intelligent systems
- The Prospects for Analogue Neural VLSI
- A Study of Early Stopping and Model Selection Applied to the Papermaking Industry
- Artificial neural network prediction of antisense oligodeoxynucleotide activity.
- Enhancing Supervised Terrain Classification with Predictive Unsupervised Learning
- Supervised Feature Ranking Using a Genetic Algorithm Optimized Artificial Neural Network
- Prediction of Drought-Resistant Genes in Arabidopsis thaliana Using SVM-RFE
- Knowledge Recovery for Continental-Scale Mineral Exploration by Neural Networks
- Neural networks for automatic speech recognition: a review
- Recent Advances in Reinforcement Learning
- Filter Sketch for Network Pruning
- Neural network architecture selection: new Bayesian perspectives in predictive modelling: Application to a soil hydrology problem
- SLRProp: A Back-Propagation Variant of Sparse Low Rank Method for DNNs Reduction
- Obtaining locally identified models: The irrelevant connection elimination scheme
- Active data selection in supervised and unsupervised learning
- Constructive feedforward neural networks for regression problems : a survey
- Adaptive parameter pruning in neural networks
- A framework to deal with interference in connectionist systems
- Hardware Learning in Analogue VLSI Neural Networks
- Autonomously Reconfigurable Artificial Neural Network on a Chip
Related papers
- Learning Multiple Layers of Features from Tiny Images
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Deep Residual Learning for Image Recognition
- Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
- ImageNet classification with deep convolutional neural networks