On the performance of single-layered neural networks.

Abstract:

:This paper studies the performance of single-layered neural networks. This study begins with the performance of single-layered neural networks trained using the outer-product rule. The outer-product rule is a suboptimal learning scheme, resulting under certain assumptions from optimal least-squares training of single-layered neural networks with respect to their analog output. Extensive analysis reveals the improvement on the network performance caused by its optimal least-squares training. The effect of the training scheme on the performance of single-layered neural networks with binary output is exhibited by experimentally comparing the performance of single-layered neural networks trained with respect to their analog and binary output.

journal_name

Biol Cybern

journal_title

Biological cybernetics

authors

Karayiannis NB,Venetsanopoulos AN

doi

10.1007/BF00203135

keywords:

subject

Has Abstract

pub_date

1992-01-01 00:00:00

pages

31-41

issue

1

eissn

0340-1200

issn

1432-0770

journal_volume

68

pub_type

杂志文章
  • Intrinsic variability of latency to first-spike.

    abstract::The assessment of the variability of neuronal spike timing is fundamental to gain understanding of latency coding. Based on recent mathematical results, we investigate theoretically the impact of channel noise on latency variability. For large numbers of ion channels, we derive the asymptotic distribution of latency, ...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/s00422-010-0384-8

    authors: Wainrib G,Thieullen M,Pakdaman K

    更新日期:2010-07-01 00:00:00

  • Internally coupled ears in living mammals.

    abstract::It is generally held that the right and left middle ears of mammals are acoustically isolated from each other, such that mammals must rely on neural computation to derive sound localisation cues. There are, however, some unusual species in which the middle ear cavities intercommunicate, in which case each ear might be...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/s00422-015-0675-1

    authors: Mason MJ

    更新日期:2016-10-01 00:00:00

  • From neuron to behavior: dynamic equation-based prediction of biological processes in motor control.

    abstract::This article presents the use of continuous dynamic models in the form of differential equations to describe and predict temporal changes in biological processes and discusses several of its important advantages over discontinuous bistable ones, exemplified on the stick insect walking system. In this system, coordinat...

    journal_title:Biological cybernetics

    pub_type: 杂志文章,评审

    doi:10.1007/s00422-011-0446-6

    authors: Daun-Gruhn S,Büschges A

    更新日期:2011-07-01 00:00:00

  • Minimum mean square error estimation of connectivity in biological neural networks.

    abstract::A minimum mean square error (MMSE) estimation scheme is employed to identify the synaptic connectivity in neural networks. This new approach can substantially reduce the amount of data and the computational cost involved in the conventional correlation methods, and is suitable for both nonstationary and stationary neu...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/BF00198088

    authors: Yang X,Shamma SA

    更新日期:1991-01-01 00:00:00

  • The construction of a simultaneous functional order in nervous systems. I. Relevance of signal covariances and signal coincidences in the construction of a functional order.

    abstract::We have developed two algorithms that construct a simultaneous functional order in a collection of neural elements using purely functional relations. The input of the first algorithm is a matrix describing the total of covariances of signals carried by the members of the neural collection. The second algorithm proceed...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/BF00318721

    authors: Toet A,Blom J,Koenderink JJ

    更新日期:1987-01-01 00:00:00

  • A neural network study of precollicular saccadic averaging.

    abstract::Saccadic averaging is the phenomenon that two simultaneously presented retinal inputs result in a saccade with an endpoint located on an intermediate position between the two stimuli. Recordings from neurons in the deeper layers of the superior colliculus have revealed neural correlates of saccade averaging, indicatin...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/s004220050450

    authors: Krommenhoek KP,Wiegerinck WA

    更新日期:1998-06-01 00:00:00

  • Reduced order multiport parallel and multidirectional neural associative memories.

    abstract::This paper proposes multiport parallel and multidirectional intraconnected associative memories of outer product type with reduced interconnections. Some new reduced order memory architectures such as k-directional and k-port parallel memories are suggested. These architectures are, also, very suitable for implementat...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/s00422-009-0310-0

    authors: Bhatti AA

    更新日期:2009-05-01 00:00:00

  • The distributed representation of vestibulo-oculomotor signals by brain-stem neurons.

    abstract::The vestibuloocular reflex and other oculomotor functions are subserved by populations of neurons operating in parallel. This distributed aspect of the system's organization has been largely ignored in previous block diagram models. Neurons that transmit oculomotor signals, such as those in the vestibular nucleus (VN)...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/BF00204592

    authors: Anastasio TJ,Robinson DA

    更新日期:1989-01-01 00:00:00

  • A central back-coupling hypothesis on the organization of motor synergies: a physical metaphor and a neural model.

    abstract::We offer a hypothesis on the organization of multi-effector motor synergies and illustrate it with the task of force production with a set of fingers. A physical metaphor, a leaking bucket, is analyzed to demonstrate that an inanimate structure can show apparent error compensation among its elements. A neural model is...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/s00422-005-0548-0

    authors: Latash ML,Shim JK,Smilga AV,Zatsiorsky VM

    更新日期:2005-03-01 00:00:00

  • Adaptive synaptogenesis constructs networks that maintain information and reduce statistical dependence.

    abstract::This report demonstrates the effectiveness of two processes in constructing simple feedforward networks which perform good transformations on their inputs. Good transformations are characterized by the minimization of two information measures: the information loss incurred with the transformation and the statistical d...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/BF00202569

    authors: Adelsberger-Mangan DM,Levy WB

    更新日期:1993-01-01 00:00:00

  • Spectro-temporal representations and time-varying spectra of evoked potentials. A methodological investigation.

    abstract::Evoked potential waveforms are generally of a dynamic, transient character. Consequently, their spectral energy distribution cannot be adequately described by time-invariant representations, such as the power density spectrum. Obviously, a spectro-temporal description is needed. Appropriate means for obtaining such de...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/BF00335365

    authors: de Weerd JP,Kap JI

    更新日期:1981-01-01 00:00:00

  • Evidence for different nonlinear summation schemes for lines and gratings at threshold.

    abstract::Within a wide class of multichannel models of the visual system it is suggested that spatial distributions of luminance are processed by the independent activation of grating detectors, or spatial frequency channels. Probability summation is often described in terms of Quick's nonlinear pooling model [Quick RF (1974) ...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/s004220050561

    authors: Meinhardt G

    更新日期:1999-09-01 00:00:00

  • Learning a grating discrimination task broadens human spatial frequency tuning.

    abstract::The effect of spatial frequency discrimination learning on spatial frequency detection tuning curves, obtained by a summation to threshold paradigm, has been investigated. Three human observers were exposed to a grating discrimination task for longer than two weeks, and their detection thresholds for compound Gabor gr...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/PL00007983

    authors: Meinhardt G

    更新日期:2001-05-01 00:00:00

  • Synchronization of neural activity is a promising mechanism of memory information processing in networks of columns.

    abstract::Synchronization of the oscillatory discharge of cortical neurons could be a part of the mechanism that is involved in cortical information processing. On the assumption that the basic functional unit is the column composed of local excitatory and inhibitory cells and generating oscillatory neural activity, a network m...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/BF00202761

    authors: Fukai T

    更新日期:1994-01-01 00:00:00

  • Computational nature of human adaptive control during learning of reaching movements in force fields.

    abstract::Learning to make reaching movements in force fields was used as a paradigm to explore the system architecture of the biological adaptive controller. We compared the performance of a number of candidate control systems that acted on a model of the neuromuscular system of the human arm and asked how well the dynamics of...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/s004220050543

    authors: Bhushan N,Shadmehr R

    更新日期:1999-07-01 00:00:00

  • Saccadic motor planning by integrating visual information and pre-information on neural dynamic fields.

    abstract::A functional model of target selection in the saccadic system is presented, incorporating elements of visual processing, motor planning, and motor control. We address the integration of visual information with pre-information, which is provided by manipulating the probability that a target appears at a certain locatio...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/BF00199055

    authors: Kopecz K,Schöner G

    更新日期:1995-06-01 00:00:00

  • Neural modeling of intrinsic and spike-discharge properties of cochlear nucleus neurons.

    abstract::The purpose of this study was to develop neurobiologically plausible models to account for the response properties of several types of cochlear nucleus neurons. Three cell types--the bushy cells, stellate cells, and fusiform cells--were selected because useful data from intracellular recordings were available for thes...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/BF00199590

    authors: Arle JE,Kim DO

    更新日期:1991-01-01 00:00:00

  • Action and behavior: a free-energy formulation.

    abstract::We have previously tried to explain perceptual inference and learning under a free-energy principle that pursues Helmholtz's agenda to understand the brain in terms of energy minimization. It is fairly easy to show that making inferences about the causes of sensory data can be cast as the minimization of a free-energy...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/s00422-010-0364-z

    authors: Friston KJ,Daunizeau J,Kilner J,Kiebel SJ

    更新日期:2010-03-01 00:00:00

  • Techniques for temporal detection of neural sensitivity to external stimulation.

    abstract::We propose a simple measure of neural sensitivity for characterizing stimulus coding. Sensitivity is defined as the fraction of neurons that show positive responses to n stimuli out of a total of N. To determine a positive response, we propose two methods: Fisherian statistical testing and a data-driven Bayesian appro...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/s00422-009-0297-6

    authors: Rodríguez FB,Huerta R

    更新日期:2009-04-01 00:00:00

  • Quantization of human motions and learning of accurate movements.

    abstract::This paper presents a mathematical model for the learning of accurate human arm movements. Its main features are that the movement is the superposition of smooth submovements, the intrinsic deviation of arm movements is considered, visual and kinesthetic feed-back are integrated in the motion control, and the movement...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/s004220050435

    authors: Burdet E,Milner TE

    更新日期:1998-04-01 00:00:00

  • Three-dimensional kinematic analysis of influence of hand orientation and joint limits on the control of arm postures and movements.

    abstract::The problems related to kinematic redundancy in both task and joint space were investigated for arm prehension movements in this paper. After a detailed analysis of kinematic redundancy of the arm, it is shown that the redundancy problem is ill posed only for the control of hand orientation. An experiment was then des...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/s004220050538

    authors: Wang X

    更新日期:1999-06-01 00:00:00

  • Quantification of directional and orientational selectivities of visual neurons to moving stimuli.

    abstract::Directional and orientational components usually coexist and are mixed in the cell's overall responses when moving optical stimuli are used to study the response characteristics of visual neurons. While these two properties were quantified with all the previous methods for data analysis, their effects could not be eff...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/BF00197609

    authors: Li B,Wang Y,Diao Y

    更新日期:1994-01-01 00:00:00

  • Conditional entropy approach for the evaluation of the coupling strength.

    abstract::A method that enables measurement of the degree of coupling between two signals is presented. The method is based on the definition of an uncoupling function calculating, by means of entropy rates, the minimum amount of independent information (i.e. the information carried by one signal which cannot be derived from th...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/s004220050549

    authors: Porta A,Baselli G,Lombardi F,Montano N,Malliani A,Cerutti S

    更新日期:1999-08-01 00:00:00

  • Analysis of bursting in a thalamic neuron model.

    abstract::We extend a quantitative model for low-voltage, slow-wave excitability based on the T-type calcium current (Wang et al. 1991) by juxtaposing it with a Hodgkin-Huxley-like model for fast sodium spiking in the high voltage regime to account for the distinct firing modes of thalamic neurons. We employ bifurcation analysi...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/BF00239616

    authors: Rush ME,Rinzel J

    更新日期:1994-01-01 00:00:00

  • Information-theoretic analysis of de-efferented single muscle spindles.

    abstract::The information transmission properties of single, de-efferented primary muscle-spindle afferents from the hind limb of the cat were investigated. The gastrocnemius medialis muscle was stretched randomly while recording spike trains from several muscle-spindle afferents in the dorsal root. Two classes of input stimuli...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/s00422-002-0341-2

    authors: Tock Y,Ljubisavljevic M,Thunberg J,Windhorst U,Inbar GF,Johansson H

    更新日期:2002-10-01 00:00:00

  • Human hand impedance characteristics during maintained posture.

    abstract::The present paper examines human hand impedance characteristics, including inertia and viscosity as well as stiffness, in multi-joint arm movements. While a subject maintains a given hand location, small external disturbances are applied to his hand by a manipulandum. The corresponding force-displacement vectors are m...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/BF00199890

    authors: Tsuji T,Morasso PG,Goto K,Ito K

    更新日期:1995-01-01 00:00:00

  • Reflexes and preflexes: on the role of sensory feedback on rhythmic patterns in insect locomotion.

    abstract::Neuromuscular systems are stabilized and controlled by both feedforward and feedback signals. Feedforward pathways driven by central pattern generators (CPGs), in conjunction with preflexive mechanical reaction forces and nonlinear muscle properties, can produce stable stereotypical gaits. Feedback is nonetheless pres...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/s00422-010-0383-9

    authors: Proctor J,Holmes P

    更新日期:2010-06-01 00:00:00

  • Behavioral analysis of differential Hebbian learning in closed-loop systems.

    abstract::Understanding closed loop behavioral systems is a non-trivial problem, especially when they change during learning. Descriptions of closed loop systems in terms of information theory date back to the 1950s, however, there have been only a few attempts which take into account learning, mostly measuring information of i...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/s00422-010-0396-4

    authors: Kulvicius T,Kolodziejski C,Tamosiunaite M,Porr B,Wörgötter F

    更新日期:2010-10-01 00:00:00

  • A model for the economical encoding of the visual image in cerebral cortex.

    abstract::We propose a model for the first stage of the cortical transformation of the visual image based on the principle that the cortex encodes the information with the minimum number of channels mathematically needed. We restrict our model to be consistent with the data on size adaptations, the known relationships of acuity...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/BF00336972

    authors: Sakitt B,Barlow HB

    更新日期:1982-01-01 00:00:00

  • Geometry-induced features of current transfer in neuronal dendrites with tonically activated conductances.

    abstract::The impact of dendritic geometry on somatopetal transfer of the current generated by steady uniform activation of excitatory synaptic conductance distributed over passive, or active (Hodgkin-Huxley type), dendrites was studied in simulated neurons. Such tonic activation was delivered to the uniform dendrite and to the...

    journal_title:Biological cybernetics

    pub_type: 杂志文章

    doi:10.1007/s004220050473

    authors: Korogod SM,Kulagina IB

    更新日期:1998-09-01 00:00:00