The Effective Number of Parameters: An Analysis of Generalization and Regularization in Nonlinear Learning Systems

No abstract is available for this paper.

• Publication year

  1991

• Venue

  Neural Information Processing Systems

• Publication date

  1991-12-02

• Fields of study

  Mathematics, Computer Science

• Identifiers

  No identifiers available.

• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Principled Architecture Selection for Neural Networks: Application to Corporate Bond Rating Prediction

  1991cited by this paper
• Note on generalization, regularization and architecture selection in nonlinear learning systems

  1991influential reference
• Spline smoothing and nonparametric regression

  1989cited by this paper
• Spline Smoothing and Nonparametric Regression.

  1989cited by this paper
• A new look at the statistical model identification

  1974cited by this paper
• Information Theory and an Extension of the Maximum Likelihood Principle

  1973cited by this paper
• Statistical predictor identification

  1970influential reference

• Measuring Neural Network Complexity via Effective Degrees of Freedom

  2026cites this paper
• Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime

  2026cites this paper
• Theory Foundation of Physics-Enhanced Residual Learning

  2025cites this paper
• Flatness After All?

  2025cites this paper
• Comparative study of teachable machine for forest fire and smoke detection by drone

  2024cites this paper
• Utilizing machine learning to predict participant response to follow-up health surveys in the Millennium Cohort Study

  2024cites this paper
• Decoupled Weight Decay for Any p Norm

  2024cites this paper
• Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond

  2024cites this paper
• Study on deviation correction and target positioning of intelligent operation robot for high-voltage switchgear

  2024cites this paper
• Automatic Regularization for Linear MMSE Filters

  2023influential citation
• A mathematical theory of relational generalization in transitive inference

  2023cites this paper
• Dense Sample Deep Learning

  2023cites this paper
• Emotion Based Music Player

  2023cites this paper
• Two-layer networks with the $$\text {ReLU}^k$$ ReLU k activation function: Barron spaces and derivative approximation

  2023cites this paper
• SANE: The phases of gradient descent through Sharpness Adjusted Number of Effective parameters

  2023cites this paper
• Generalization of linear and non-linear support vector machine in multiple fields: a review

  2023cites this paper
• Regularization and tempering for a moment‐matching localized particle filter

  2022cites this paper
• Accuracy and self-validation of automated bone age determination

  2022cites this paper
• Performance of Akaike Information Criterion and Bayesian Information Criterion in Selecting Partition Models and Mixture Models

  2022cites this paper
• Error Amplification When Updating Deployed Machine Learning Models

  2022cites this paper
• Forest Fires Detection using Deep Transfer Learning

  2022cites this paper
• Perceptron: Learning, Generalization, Model Selection, Fault Tolerance, and Role in the Deep Learning Era

  2022cites this paper
• Optimal ratio for data splitting

  2022cites this paper
• A generalized AIC for models with singularities and boundaries

  2022cites this paper
• Multiobjective Linear Ensembles for Robust and Sparse Training of Few-Bit Neural Networks

  2022cites this paper
• Learning Neural Networks without Lazy Weights

  2022cites this paper
• Information-Theoretic Characterization of the Generalization Error for Iterative Semi-Supervised Learning

  2021cites this paper
• A Generalization Gap Estimation for Overparameterized Models via the Langevin Functional Variance

  2021cites this paper
• Sparse Bayesian Learning With Weakly Informative Hyperprior and Extended Predictive Information Criterion

  2021cites this paper
• Regularization methods vs large training sets

  2020cites this paper
• Channel Profile Independent Usage of Convolutional Neural Networks for Receiver Chain Optimization

  2020influential citation
• Relevance Vector Machine with Weakly Informative Hyperprior and Extended Predictive Information Criterion

  2020cites this paper
• Potential of Artificial Intelligence for Estimating Japanese Fetal Weights.

  2020cites this paper
• Using artificial neural networks to represent a diesel–biodiesel engine

  2020cites this paper
• R ETHINKING P ARAMETER C OUNTING : E FFECTIVE D IMENSIONALITY R EVISITED

  2020cites this paper
• Discriminative Regularized Auto-Encoder for Early Detection of Knee OsteoArthritis: Data from the Osteoarthritis Initiative

  2020cites this paper
• An introduction to deep learning in medical physics: advantages, potential, and challenges

  2020cites this paper
• Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited

  2020cites this paper
• Grouped variable selection in high dimensional partially linear additive Cox model

  2019cites this paper
• Image Recognition Based on Combined Filters with Pseudoinverse Learning Algorithm

  2019cites this paper
• The Role of Neural Network Activation Functions

  2019cites this paper
• Neural models for information retrieval: towards asymmetry sensitive approaches based on attention models. (Modèles neuronaux pour la recherche d'information : vers des approches sensibles à l'asymétrie basées sur des modèles d'attention)

  2019cites this paper
• Grouped variable selection in high dimensional partially linear additive Cox model

  2019cites this paper
• Fleet route selection prediction problem based on support vector machine

  2019cites this paper
• Application of deep learning to the classification of uterine cervical squamous epithelial lesion from colposcopy images combined with HPV types

  2019cites this paper
• KUNSTLICHE INTELLIGENZ Discovering Proble 1 n Solutions With Low Kolmogorov Complexity and High Generalization Capability

  2019cites this paper
• Feasibility of predicting live birth by combining conventional embryo evaluation with artificial intelligence applied to a blastocyst image in patients classified by age

  2019cites this paper
• A Deep Learning Based Attack for The Chaos-based Image Encryption

  2019cites this paper
• Grouped variable selection in high dimensional partially linear additive Cox model

  2019cites this paper
• Training Binarized Neural Networks Using MIP and CP

  2019cites this paper
• Feasibility of deep learning for predicting live birth from a blastocyst image in patients classified by age

  2019cites this paper
• Social Vulnerability Assessment Using Artificial Neural Network (ANN) Model for Earthquake Hazard in Tabriz City, Iran

  2018cites this paper
• Model Structure Selection Using an Integrated Forward Orthogonal Search Algorithm Interfered with Squared Correlation and Mutual Information

  2018cites this paper
• Hints

  2018cites this paper
• Fitness Landscape Analysis of Weight-Elimination Neural Networks

  2018cites this paper
• Grouped variable selection in high dimensional partially linear additive Cox model

  2018cites this paper
• Spatially continuous dynamic factor modeling with basis expansion using L2 penalized likelihood

  2018influential citation
• 4 Artificial Neural Networks for Material Identification , Mineralogy and Analytical Geochemistry Based on Laser-Induced Breakdown Spectroscopy

  2018cites this paper
• Model Selection

  2018cites this paper
• Term Extraction as Sequence Labeling Task using Recurrent Neural Networks

  2018cites this paper
• The Outer Product Structure of Neural Network Derivatives

  2018cites this paper
• A Primer for Model Selection: The Decisive Role of Model Complexity

  2018cites this paper
• The Effect Of Foreign Direct Investment Inflows On Residential Real Estate Prices In Kenya

  2018cites this paper
• Brain Age Prediction using Magnetic Resonance Imaging and Deep Learning

  2018cites this paper
• Thermodynamic integration for dynamic causal models

  2018cites this paper
• SVR-based prediction of carbon emissions from energy consumption in Henan Province

  2018cites this paper
• Frequentist Model Averaging

  2018cites this paper
• Short-Term Forecasting of Electric Loads Using Nonlinear Autoregressive Artificial Neural Networks with Exogenous Vector Inputs

  2017cites this paper
• On Optimal Generalizability in Parametric Learning

  2017cites this paper
• Determining spatio-temporal metrics that distinguish play outcomes in field hockey

  2017cites this paper
• On the Complexity of Item Response Theory Models

  2017cites this paper
• Lightweight Neural Networks

  2017cites this paper
• A novel volumetric efficiency model for spark ignition engines equipped with variable valve timing and variable valve lift Part 1: model development

  2017cites this paper
• Medicine Open Access book publisher

  2017cites this paper
• On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations

  2017cites this paper
• Software defect prediction using stacked denoising autoencoders and two-stage ensemble learning

  2017cites this paper
• Spectrophotometric prediction of pre-colored fiber blends with a hybrid model based on artificial neural network and Stearns–Noechel model

  2017cites this paper
• Human-Drone interaction for relationship building using emotion recognition

  2017cites this paper
• Pedestrian Counting using Deep Models Trained on Synthetically Generated Images

  2017influential citation
• Input Layer Regularization of Multilayer Feedforward Neural Networks

  2017cites this paper
• Bus travel time prediction using a time-space discretization approach

  2017cites this paper
• Mound Breakwater Design in Depth-Limited Breaking Wave Conditions

  2017cites this paper
• Approximation of nonlinear term in model robotic

  2017cites this paper
• Theses and Dissertations 2010 Grouped variable selection in high dimensional partially linear additive Cox model

  2016cites this paper
• Sensitivity based selection of inputs and delays for NARX models

  2016cites this paper
• Automatic feature extraction based structure decomposition method for multi-classification

  2016cites this paper
• Methodological development for selection of significant predictors explaining fatal road accidents.

  2016cites this paper
• An Exercise and Sports Equipment Recognition System

  2016cites this paper
• Towards integrating intelligence in electronic skin

  2016cites this paper
• Acoustic and conversational speech analysis of depressed adolescents and their parents

  2016cites this paper
• The role of data sample size and dimensionality in neural network based forecasting of building heating related variables

  2016influential citation
• Classifying Unidentified Gamma-ray Sources

  2016cites this paper
• Real-Time Signal Extraction with Regularized Multivariate Direct Filter Approach

  2016influential citation
• Sensitivity based selection of inputs and delays for nonlinear ARX models

  2015influential citation
• Variable selection for prediction of time series from smart city

  2015influential citation
• An Integrative Framework of Model Evaluation

  2015cites this paper
• Control Power Optimization using Artificial Intelligence for Hybrid Wing Body Aircraft

  2015cites this paper
• An Integrative Framework of Model Evaluation

  2015cites this paper
• Regularized Linear and Nonlinear Autoregressive Models for Dengue Confirmed-Cases Prediction

  2015cites this paper
• pplication of artificial neural networks for the soil moisture retrieval rom active and passive microwave spaceborne sensors

  2015cites this paper