Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks

DOI10.1126/science.247.4945.978zbMath1226.92005OpenAlexW2086472796WikidataQ52242258 ScholiaQ52242258MaRDI QIDQ3101316

Tomaso Poggio, Federico Girosi

Publication date: 28 November 2011

Published in: Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1126/science.247.4945.978

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items

Efficient input-output model representations, Dynamic sizing of multilayer perceptrons, Another look at statistical learning theory and regularization, The numerical solution of linear ordinary differential equations by feedforward neural networks, Nonlinear modeling and prediction by successive approximation using radial basis functions, On the stability of reproducing kernel Hilbert spaces of discrete-time impulse responses, Visual RBF network design based on star coordinates, Extending the smoothing spline estimate, A new adaptive polynomial neural network, New approach to applying neural network in nonlinear dynamic model, Solution of nonlinear ordinary differential equations by feedforward neural networks, On radial basis function nets and kernel regression: Statistical consistency, convergence rates, and receptive field size, Accuracy of suboptimal solutions to kernel principal component analysis, Topological feature maps with self-organized lateral connections: A population-coded, one-layer model of associative memory, Optimal speech motor control and token-to-token variability: a Bayesian modeling approach, The generalized cross validation filter, Training a reciprocal-sigmoid classifier by feature scaling-space, Facial expression synthesis using manifold learning and belief propagation, Estimation of Lyapunov spectrum and model selection for a chaotic time series, System impulse response identification using a multiresolution neural network, Distributed parametric and nonparametric regression with on-line performance bounds computation, Data processing and feature screening in function approximation: An application to neural networks, Trigonometric RBF neural robust controller design for a class of nonlinear system with linear input unmodeled dynamics, Improving nonlinear modeling capabilities of functional link adaptive filters, Many regression algorithms, one unified model: a review, OCReP: an optimally conditioned regularization for pseudoinversion based neural training, A neurofuzzy approach to variational problems by using Gaussian membership functions, Dual adaptive control of nonlinear stochastic systems using neural networks, Comparing fixed and variable-width Gaussian networks, Trends in extreme learning machines: a review, Robust sequential learning of feedforward neural networks in the presence of heavy-tailed noise, Mesh-based and meshless design and approximation of scalar functions, A novel hybrid RBF neural networks model as a forecaster, An accelerated procedure for solving binary optimization problems, Predicate logic based image grammars for complex pattern recognition, Approximation of function and its derivatives using radial basis function networks, Machine learning of linear differential equations using Gaussian processes, Prediction error identification of linear systems: a nonparametric Gaussian regression approach, Hidden physics models: machine learning of nonlinear partial differential equations, A numerical method for minimum distance estimation problems, Efficient cross-validation for kernelized least-squares regression with sparse basis expansions, Bridging logic and kernel machines, Support vector machines with applications, The use of unlabeled data in predictive modeling, Quantile regression with \(\ell_1\)-regularization and Gaussian kernels, Bayesian ARTMAP for regression, A growing and pruning sequential learning algorithm of hyper basis function neural network for function approximation, Geometric preprocessing and neurocomputing for pattern recognition and pose estimation., Kernel methods in system identification, machine learning and function estimation: a survey, A neural network method for nonlinear time series analysis, Kernel methods in machine learning, Analog-symbolic memory that tracks via reconsolidation, Inversion of Fredholm integral equations of the first kind with fully connected neural networks, Sparse plus low rank network identification: a nonparametric approach, Nonlinear regression modeling via regularized radial basis function networks, Semantic-based regularization for learning and inference, Neural networks for control systems - a survey, A mixed-integer programming approach to GRNN parameter estimation, Discriminatively regularized least-squares classification, Decision theoretic generalizations of the PAC model for neural net and other learning applications, An analysis of numerical issues in neural training by pseudoinversion, Statistical physics of vaccination, Approximation by superposition of sigmoidal and radial basis functions, From basis functions to basis fields: Vector field approximation from sparse data, Vector field approximation: A computational paradigm for motor control and learning, Topology and simulations of a hierarchical Markovian radial basis function neural network classifier, Application of the clipping procedure to the binary minimization of a quadratic functional, Compared techniques for the critical submergence of an intake in water flow, Some extensions of radial basis functions and their applications in artificial intelligence, Improved accuracy of multiquadric interpolation using variable shape parameters, Function approximation on non-Euclidean spaces, A hybrid approach for the random dynamics of uncertain systems under stochastic loading, Linguistic neurocomputing: The design of neural networks in the framework of fuzzy sets, Establishing criteria to ensure successful feedforward artificial neural network modelling of mechanical systems, Regularized vector field learning with sparse approximation for mismatch removal, Fast exact leave-one-out cross-validation of sparse least-squares support vector machines, Fast computation of smoothing splines subject to equality constraints, Approximation analysis of feedforward regular fuzzy neural network with two hidden layers, Learning with generalization capability by kernel methods of bounded complexity, From linear to nonlinear identification: one step at a time, A new kernel-based approach for linear system identification, Machine learning problems from optimization perspective, Efficient exploration through active learning for value function approximation in reinforcement learning, Regularized multiple-set canonical correlation analysis, Wavelet estimation by Bayesian thresholding and model selection, Radial basis function network learning using localized generalization error bound, System identification using kernel-based regularization: new insights on stability and consistency issues, Mitochondrial SNPs associated with Japanese centenarians, Alzheimer's patients, and Parkinson's patients, Using radial basis function networks and significance testing to select effective siRNA sequences, Modelling public transport trips by radial basis function neural networks, Optimal interpolation of gravity maps using a modified neural network, On simultaneous approximations by radial basis function neural networks, Geometric selection of centers for radial basis function approximations involved in intensive computer simulations, Complementarity and equivalence relationships between convex fuzzy systems with symmetry restrictions and wavelets, Representing three-dimensional objects by sets of activities of receptive fields, Approximation properties of local bases assembled from neural network transfer functions, Robust fuzzy control of nonlinear systems using shape-adaptive radial basis functions, BEM-NN computation of generalised Newtonian flows, Recognition of 3D flexible objects by GRBF, Robust EM kernel-based methods for linear system identification, Unnamed Item, Event-triggered adaptive decentralised control for switched interconnected nonlinear systems with unmodeled dynamics and full state constraints, Hierarchical regularization networks for sparsification based learning on noisy datasets, Measuring Complexity of Learning Schemes Using Hessian-Schatten Total Variation, Using Multilayer Perceptron Computation to Discover Ideal Insect Olfactory Receptor Combinations in the Mosquito and Fruit Fly for an Efficient Electronic Nose, Foundations of Support Constraint Machines, Deep Restricted Kernel Machines Using Conjugate Feature Duality, COMPARATIVE STUDY OF WAVELET BASED NEURAL NETWORK AND NEURO-FUZZY SYSTEMS, Model-based update in task-level feedforward control using on-line approximation, Demand forecasting of perishable farm products using support vector machine, Neuro-adaptive cooperative tracking control with prescribed performance of unknown higher-order nonlinear multi-agent systems, Adaptive robust nonlinear control of a magnetic levitation system, Stable adaptive neuro-control design via Lyapunov function derivative estimation, Control of chaotic dynamical systems using radial basis function network approximators, RADIAL BASIS FUNCTION NETWORKS AS CHAOTIC GENERATORS FOR SECURE COMMUNICATION SYSTEMS, Unnamed Item, An Invariance Property of Predictors in Kernel-Induced Hypothesis Spaces, Online Adaptive Decision Trees: Pattern Classification and Function Approximation, Regularization: From Inverse Problems to Large-Scale Machine Learning, A comparative analysis of neural network performances in astronomical imaging, Solving inverse-PDE problems with physics-aware neural networks, RBF-based neurodynamic nearest neighbor classification in real pattern space, Neural coding of categories: information efficiency and optimal population codes, Radial basis function networks for internal model control, Stochastic minimization with adaptive memory, Global optimization issues in deep network regression: an overview, An intelligent-agent-based fuzzy group decision making model for financial multicriteria decision support: The case of credit scoring, Approximation properties of a multilayered feedforward artificial neural network, Optimally regularised kernel Fisher discriminant classification, Development of simple fitness landscapes for peptides by artificial neural filter systems, A Recursive Local Polynomial Approximation Method Using Dirichlet Clouds and Radial Basis Functions, On Different Facets of Regularization Theory, Nonparametric identification of population models via Gaussian processes, Force/position tracking for a robotic manipulator in compliant contact with a surface using neuro-adaptive control, A novel interpretation for the collicular role in saccade generation, Robust estimation of tangent maps and Liapunov spectra, Increasing the attraction area of the global minimum in the binary optimization problem, Gaussian neural networks for control function implementation, Nonlinear black-box modeling in system identification: A unified overview, Nonlinear black-box models in system identification: Mathematical foundations, Feature-based methods for large scale dynamic programming, On a new family of radial basis functions: mathematical analysis and applications to option pricing, Sigmoidal theory, Kernel-based methods for Volterra series identification, Forward and backward least angle regression for nonlinear system identification, Solvable models of layered neural networks based on their differential structure, Limitations of the approximation capabilities of neural networks with one hidden layer, Beurling-Lax type theorems and Cuntz relations, Approximation-based fixed-time adaptive tracking control for a class of uncertain nonlinear pure-feedback systems, Generalized multiscale radial basis function networks, Incremental acquisition of multiple nonlinear forward models based on differentiation process of schema model, On the mathematical foundations of stable RKHSs, Information Processing in Dendritic Trees, Data-driven forward-inverse problems for Yajima-Oikawa system using deep learning with parameter regularization, Convergence analysis of sliding mode trajectories in multi-objective neural networks learning, Improving importance estimation in pool-based batch active learning for approximate linear regression, Overtraining, regularization and searching for a minimum, with application to neural networks, Primal and dual model representations in kernel-based learning, Recovery guarantees for polynomial coefficients from weakly dependent data with outliers, Using radial basis function networks for function approximation and classification, Solutions of nonlinear control and estimation problems in reproducing kernel Hilbert spaces: existence and numerical determination, Knowledge-based Green's kernel for support vector regression, Adaptive kernel methods using the balancing principle, Sequential approximate optimization using radial basis function network for engineering optimization, An efficient algorithm for learning to rank from preference graphs, Time series analysis and prediction on complex dynamical behavior observed in a blast furnace, Generalization in Interactive Networks: The Benefits of Inhibitory Competition and Hebbian Learning, Regularized orthogonal least squares algorithm for constructing radial basis function networks, Bayes and empirical Bayes semi-blind deconvolution using eigenfunctions of a prior covariance, Effective implementation to reduce execution time of a low-rank matrix approximation problem, Kernel Absolute Summability Is Sufficient but Not Necessary for RKHS Stability, A unifying representer theorem for inverse problems and machine learning, Biometric scores fusion based on total error rate minimization, Modified constrained learning algorithms incorporating additional functional constraints into neural networks, A tutorial on kernel methods for categorization, Fixed-size least squares support vector machines: A large scale application in electrical load forecasting, Massively parallel algorithms from physics and biology, The Shape of a Local Minimum and the Probability of its Detection in Random Search, Application of radial basis function and generalized regression neural networks in nonlinear utility function specification for travel mode choice modelling, Classifier learning with a new locality regularization method, Local prediction of nonlinear time series using support vector regression, An extension of the quadratic error function for learning imprecise data in multivariate nonlinear regression, Numerical method for estimating multivariate conditional distributions, Neuro-fuzzy GMDH and its application to modelling grinding characteristics, Improved constrained learning algorithms by incorporating additional functional constraints into neural networks, Identification of geometric parameters of drawbead in metal forming processes, Additive regularization trade-off: fusion of training and validation levels in kernel methods, Consistent Sobolev regression via fuzzy systems with overlapping concepts, Locally linear metric adaptation with application to semi-supervised clustering and image retrieval, Orientation selection using modified FCM for competitive code-based palmprint recognition, On the Complexity of Computing and Learning with Multiplicative Neural Networks, The weight-decay technique in learning from data: an optimization point of view, Relaxational metric adaptation and its application to semi-supervised clustering and content-based image retrieval, Neural Networks for Localized Approximation, Random Projection RBF Nets for Multidimensional Density Estimation, Solving first-order differential equations of \(Z\)-numbers' initial value using radial basic function, Generalized Hermite Interpolation Via Matrix-Valued Conditionally Positive Definite Functions, Discriminative training via minimization of risk estimates based on Parzen smoothing, A bio-basis function neural network for protein peptide cleavage activity characterisation, Support vector machines: a nonlinear modelling and control perspective, A new approach for function approximation incorporating adaptive particle swarm optimization and a priori information, Classification Of Human Faces Using Karhunen-LoÉve Decomposition And Radial Basis Function Neural Networks, Stable sequential identification of continuous nonlinear dynamical systems by growing radial basis function networks, Locally induced Gaussian processes for large-scale simulation experiments, Parametric Gaussian process regression for big data, An approach for constructing complex discriminating surfaces based on Bayesian interference of the maximum entropy, Sparse radial basis function approximation with spatially variable shape parameters, Nonlinear system identification via data augmentation, Forecasting vertical ground surface movement from shrinking/swelling soils with artificial neural networks, Extreme entropy machines: robust information theoretic classification, A global implicit function theorem without initial point and its applications to control of non-affine systems of high dimensions, Numerical Gaussian Processes for Time-Dependent and Nonlinear Partial Differential Equations, Generalized asymmetrical bidirectional associative memory for multiple association, Unnamed Item, Fuzzy systems with overlapping Gaussian concepts: Approximation properties in Sobolev norms, Texture analysis by accurate identification of simple Markovian models, Unnamed Item, Parameter conditions for monotonic Takagi-Sugeno-Kang fuzzy system, Unnamed Item