Regularized neural networks: some convergence rate results.


:In a recent paper, Poggio and Girosi (1990) proposed a class of neural networks obtained from the theory of regularization. Regularized networks are capable of approximating arbitrarily well any continuous function on a compactum. In this paper we consider in detail the learning problem for the one-dimensional case. We show that in the case of output data observed with noise, regularized networks are capable of learning and approximating (on compacta) elements of certain classes of Sobolev spaces, known as reproducing kernel Hilbert spaces (RKHS), at a nonparametric rate that optimally exploits the smoothness properties of the unknown mapping. In particular we show that the total squared error, given by the sum of the squared bias and the variance, will approach zero at a rate of n(-2m)/(2m+1), where m denotes the order of differentiability of the true unknown function. On the other hand, if the unknown mapping is a continuous function but does not belong to an RKHS, then there still exists a unique regularized solution, but this is no longer guaranteed to converge in mean square to a well-defined limit. Further, even if such a solution converges, the total squared error is bounded away from zero for all n sufficiently large.


Neural Comput


Neural computation


Corradi V,White H




Has Abstract


1995-11-01 00:00:00












  • Robust boosting algorithm against mislabeling in multiclass problems.

    abstract::We discuss robustness against mislabeling in multiclass labels for classification problems and propose two algorithms of boosting, the normalized Eta-Boost.M and Eta-Boost.M, based on the Eta-divergence. Those two boosting algorithms are closely related to models of mislabeling in which the label is erroneously exchan...

    journal_title:Neural computation

    pub_type: 信件


    authors: Takenouchi T,Eguchi S,Murata N,Kanamori T

    更新日期:2008-06-01 00:00:00

  • Spike train decoding without spike sorting.

    abstract::We propose a novel paradigm for spike train decoding, which avoids entirely spike sorting based on waveform measurements. This paradigm directly uses the spike train collected at recording electrodes from thresholding the bandpassed voltage signal. Our approach is a paradigm, not an algorithm, since it can be used wit...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Ventura V

    更新日期:2008-04-01 00:00:00

  • Distributed control of uncertain systems using superpositions of linear operators.

    abstract::Control in the natural environment is difficult in part because of uncertainty in the effect of actions. Uncertainty can be due to added motor or sensory noise, unmodeled dynamics, or quantization of sensory feedback. Biological systems are faced with further difficulties, since control must be performed by networks o...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Sanger TD

    更新日期:2011-08-01 00:00:00

  • Populations of tightly coupled neurons: the RGC/LGN system.

    abstract::A mathematical model, of general character for the dynamic description of coupled neural oscillators is presented. The population approach that is employed applies equally to coupled cells as to populations of such coupled cells. The formulation includes stochasticity and preserves details of precisely firing neurons....

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Sirovich L

    更新日期:2008-05-01 00:00:00

  • A unifying view of wiener and volterra theory and polynomial kernel regression.

    abstract::Volterra and Wiener series are perhaps the best-understood nonlinear system representations in signal processing. Although both approaches have enjoyed a certain popularity in the past, their application has been limited to rather low-dimensional and weakly nonlinear systems due to the exponential growth of the number...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Franz MO,Schölkopf B

    更新日期:2006-12-01 00:00:00

  • Dynamics of learning near singularities in layered networks.

    abstract::We explicitly analyze the trajectories of learning near singularities in hierarchical networks, such as multilayer perceptrons and radial basis function networks, which include permutation symmetry of hidden nodes, and show their general properties. Such symmetry induces singularities in their parameter space, where t...

    journal_title:Neural computation

    pub_type: 信件


    authors: Wei H,Zhang J,Cousseau F,Ozeki T,Amari S

    更新日期:2008-03-01 00:00:00

  • Connecting cortical and behavioral dynamics: bimanual coordination.

    abstract::For the paradigmatic case of bimanual coordination, we review levels of organization of behavioral dynamics and present a description in terms of modes of behavior. We briefly review a recently developed model of spatiotemporal brain activity that is based on short- and long-range connectivity of neural ensembles. Thi...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Jirsa VK,Fuchs A,Kelso JA

    更新日期:1998-11-15 00:00:00

  • A bio-inspired, computational model suggests velocity gradients of optic flow locally encode ordinal depth at surface borders and globally they encode self-motion.

    abstract::Visual navigation requires the estimation of self-motion as well as the segmentation of objects from the background. We suggest a definition of local velocity gradients to compute types of self-motion, segment objects, and compute local properties of optical flow fields, such as divergence, curl, and shear. Such veloc...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Raudies F,Ringbauer S,Neumann H

    更新日期:2013-09-01 00:00:00

  • On the classification capability of sign-constrained perceptrons.

    abstract::The perceptron (also referred to as McCulloch-Pitts neuron, or linear threshold gate) is commonly used as a simplified model for the discrimination and learning capability of a biological neuron. Criteria that tell us when a perceptron can implement (or learn to implement) all possible dichotomies over a given set of ...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Legenstein R,Maass W

    更新日期:2008-01-01 00:00:00

  • Dynamic Neural Turing Machine with Continuous and Discrete Addressing Schemes.

    abstract::We extend the neural Turing machine (NTM) model into a dynamic neural Turing machine (D-NTM) by introducing trainable address vectors. This addressing scheme maintains for each memory cell two separate vectors, content and address vectors. This allows the D-NTM to learn a wide variety of location-based addressing stra...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Gulcehre C,Chandar S,Cho K,Bengio Y

    更新日期:2018-04-01 00:00:00

  • A simple Hebbian/anti-Hebbian network learns the sparse, independent components of natural images.

    abstract::Slightly modified versions of an early Hebbian/anti-Hebbian neural network are shown to be capable of extracting the sparse, independent linear components of a prefiltered natural image set. An explanation for this capability in terms of a coupling between two hypothetical networks is presented. The simple networks pr...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Falconbridge MS,Stamps RL,Badcock DR

    更新日期:2006-02-01 00:00:00

  • Similarity, connectionism, and the problem of representation in vision.

    abstract::A representational scheme under which the ranking between represented similarities is isomorphic to the ranking between the corresponding shape similarities can support perfectly correct shape classification because it preserves the clustering of shapes according to the natural kinds prevailing in the external world. ...

    journal_title:Neural computation

    pub_type: 杂志文章,评审


    authors: Edelman S,Duvdevani-Bar S

    更新日期:1997-05-15 00:00:00

  • Formal modeling of robot behavior with learning.

    abstract::We present formal specification and verification of a robot moving in a complex network, using temporal sequence learning to avoid obstacles. Our aim is to demonstrate the benefit of using a formal approach to analyze such a system as a complementary approach to simulation. We first describe a classical closed-loop si...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Kirwan R,Miller A,Porr B,Di Prodi P

    更新日期:2013-11-01 00:00:00

  • Temporal sequence learning, prediction, and control: a review of different models and their relation to biological mechanisms.

    abstract::In this review, we compare methods for temporal sequence learning (TSL) across the disciplines machine-control, classical conditioning, neuronal models for TSL as well as spike-timing-dependent plasticity (STDP). This review introduces the most influential models and focuses on two questions: To what degree are reward...

    journal_title:Neural computation

    pub_type: 杂志文章,评审


    authors: Wörgötter F,Porr B

    更新日期:2005-02-01 00:00:00

  • Computation in a single neuron: Hodgkin and Huxley revisited.

    abstract::A spiking neuron "computes" by transforming a complex dynamical input into a train of action potentials, or spikes. The computation performed by the neuron can be formulated as dimensional reduction, or feature detection, followed by a nonlinear decision function over the low-dimensional space. Generalizations of the ...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Agüera y Arcas B,Fairhall AL,Bialek W

    更新日期:2003-08-01 00:00:00

  • Discriminant component pruning. Regularization and interpretation of multi-layered back-propagation networks.

    abstract::Neural networks are often employed as tools in classification tasks. The use of large networks increases the likelihood of the task's being learned, although it may also lead to increased complexity. Pruning is an effective way of reducing the complexity of large networks. We present discriminant components pruning (D...

    journal_title:Neural computation

    pub_type: 杂志文章,评审


    authors: Koene RA,Takane Y

    更新日期:1999-04-01 00:00:00

  • Parameter Identifiability in Statistical Machine Learning: A Review.

    abstract::This review examines the relevance of parameter identifiability for statistical models used in machine learning. In addition to defining main concepts, we address several issues of identifiability closely related to machine learning, showing the advantages and disadvantages of state-of-the-art research and demonstrati...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Ran ZY,Hu BG

    更新日期:2017-05-01 00:00:00

  • Robustness of connectionist swimming controllers against random variation in neural connections.

    abstract::The ability to achieve high swimming speed and efficiency is very important to both the real lamprey and its robotic implementation. In previous studies, we used evolutionary algorithms to evolve biologically plausible connectionist swimming controllers for a simulated lamprey. This letter investigates the robustness ...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Or J

    更新日期:2007-06-01 00:00:00

  • On the slow convergence of EM and VBEM in low-noise linear models.

    abstract::We analyze convergence of the expectation maximization (EM) and variational Bayes EM (VBEM) schemes for parameter estimation in noisy linear models. The analysis shows that both schemes are inefficient in the low-noise limit. The linear model with additive noise includes as special cases independent component analysis...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Petersen KB,Winther O,Hansen LK

    更新日期:2005-09-01 00:00:00

  • Topographic mapping of large dissimilarity data sets.

    abstract::Topographic maps such as the self-organizing map (SOM) or neural gas (NG) constitute powerful data mining techniques that allow simultaneously clustering data and inferring their topological structure, such that additional features, for example, browsing, become available. Both methods have been introduced for vectori...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Hammer B,Hasenfuss A

    更新日期:2010-09-01 00:00:00

  • Whence the Expected Free Energy?

    abstract::The expected free energy (EFE) is a central quantity in the theory of active inference. It is the quantity that all active inference agents are mandated to minimize through action, and its decomposition into extrinsic and intrinsic value terms is key to the balance of exploration and exploitation that active inference...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Millidge B,Tschantz A,Buckley CL

    更新日期:2021-01-05 00:00:00

  • Sequential triangle strip generator based on Hopfield networks.

    abstract::The important task of generating the minimum number of sequential triangle strips (tristrips) for a given triangulated surface model is motivated by applications in computer graphics. This hard combinatorial optimization problem is reduced to the minimum energy problem in Hopfield nets by a linear-size construction. I...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Síma J,Lnĕnicka R

    更新日期:2009-02-01 00:00:00

  • Bayesian framework for least-squares support vector machine classifiers, gaussian processes, and kernel Fisher discriminant analysis.

    abstract::The Bayesian evidence framework has been successfully applied to the design of multilayer perceptrons (MLPs) in the work of MacKay. Nevertheless, the training of MLPs suffers from drawbacks like the nonconvex optimization problem and the choice of the number of hidden units. In support vector machines (SVMs) for class...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Van Gestel T,Suykens JA,Lanckriet G,Lambrechts A,De Moor B,Vandewalle J

    更新日期:2002-05-01 00:00:00

  • Statistical computer model analysis of the reciprocal and recurrent inhibitions of the Ia-EPSP in α-motoneurons.

    abstract::We simulate the inhibition of Ia-glutamatergic excitatory postsynaptic potential (EPSP) by preceding it with glycinergic recurrent (REN) and reciprocal (REC) inhibitory postsynaptic potentials (IPSPs). The inhibition is evaluated in the presence of voltage-dependent conductances of sodium, delayed rectifier potassium,...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Gradwohl G,Grossman Y

    更新日期:2013-01-01 00:00:00

  • Modeling short-term synaptic depression in silicon.

    abstract::We describe a model of short-term synaptic depression that is derived from a circuit implementation. The dynamics of this circuit model is similar to the dynamics of some theoretical models of short-term depression except that the recovery dynamics of the variable describing the depression is nonlinear and it also dep...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Boegerhausen M,Suter P,Liu SC

    更新日期:2003-02-01 00:00:00

  • Synchronized firings in the networks of class 1 excitable neurons with excitatory and inhibitory connections and their dependences on the forms of interactions.

    abstract::Synchronized firings in the networks of class 1 excitable neurons with excitatory and inhibitory connections are investigated, and their dependences on the forms of interactions are analyzed. As the forms of interactions, we treat the double exponential coupling and the interactions derived from it: pulse coupling, ex...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Kanamaru T,Sekine M

    更新日期:2005-06-01 00:00:00

  • A Unifying Framework of Synaptic and Intrinsic Plasticity in Neural Populations.

    abstract::A neuronal population is a computational unit that receives a multivariate, time-varying input signal and creates a related multivariate output. These neural signals are modeled as stochastic processes that transmit information in real time, subject to stochastic noise. In a stationary environment, where the input sig...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Leugering J,Pipa G

    更新日期:2018-04-01 00:00:00

  • On the emergence of rules in neural networks.

    abstract::A simple associationist neural network learns to factor abstract rules (i.e., grammars) from sequences of arbitrary input symbols by inventing abstract representations that accommodate unseen symbol sets as well as unseen but similar grammars. The neural network is shown to have the ability to transfer grammatical kno...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Hanson SJ,Negishi M

    更新日期:2002-09-01 00:00:00

  • Inhibition and Excitation Shape Activity Selection: Effect of Oscillations in a Decision-Making Circuit.

    abstract::Decision making is a complex task, and its underlying mechanisms that regulate behavior, such as the implementation of the coupling between physiological states and neural networks, are hard to decipher. To gain more insight into neural computations underlying ongoing binary decision-making tasks, we consider a neural...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Bose T,Reina A,Marshall JAR

    更新日期:2019-05-01 00:00:00

  • Toward a biophysically plausible bidirectional Hebbian rule.

    abstract::Although the commonly used quadratic Hebbian-anti-Hebbian rules lead to successful models of plasticity and learning, they are inconsistent with neurophysiology. Other rules, more physiologically plausible, fail to specify the biological mechanism of bidirectionality and the biological mechanism that prevents synapses...

    journal_title:Neural computation

    pub_type: 杂志文章


    authors: Grzywacz NM,Burgi PY

    更新日期:1998-04-01 00:00:00