Self-organization of orientation maps in a formal neuron model using a cluster learning rule

Kuroiwa, Jousuke; Inawashiro, Sakari; Miyake, Shōgo; Aso, Hirotomo

doi:10.1016/s0893-6080(99)00081-7

Cited by 7 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here the cluster learning rule means that a synaptic connection between a presynaptic and a postsynaptic neuron is strengthened by the simultaneous activation of the presynaptic neuron and of neurons located near the postsynaptic neuron. A Self-Consistent Monte Carlo (SCMC) method with the use of both an inhibitory neuron pool and the cluster learning rule successfully reproduced plausible orientation preference maps similar to experimental observations [14][15][16][17].…”

Section: Introductionmentioning

confidence: 80%

“…In 'a cluster learning rule', a synaptic connection s ik is strengthened by simultaneous activation of an input neuron k and a cluster of output neurons j which are located close to the output neuron i. The cluster learning rule is incorporated into learning equations as follows [14][15][16]:…”

Section: Cluster Learning Rulementioning

confidence: 99%

“…If we continue to present input patterns for a long duration much larger than the learning time constant, steady values of the synaptic connections will be achieved [14][15][16]:…”

Section: Steady State Of the Learningmentioning

confidence: 99%

“…The nonlinear equations corresponded to distributed magnetic moments of a three dimensional Ising-spin system described by a Hamiltonian [13]. Further, besides a usual Hebbian learning rule, we introduced 'a cluster learning rule' based on the physical picture of interactions between Ising-spins [14][15][16][17]. Here the cluster learning rule means that a synaptic connection between a presynaptic and a postsynaptic neuron is strengthened by the simultaneous activation of the presynaptic neuron and of neurons located near the postsynaptic neuron.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Formation of an Orientation Preference Map - Gradual Inhibition Method

Inawashiro

Kuroiwa²,

Nakamura

et al. 2002

Neural Computing & Applications

View full text Add to dashboard Cite

Formation of an orientation preference map due to external visual stimuli in the primary visual area of the cerebral cortex is investigated in a two-layered neural network model, where a cluster learning rule is used together with ordinary Hebbian learning rule. We succeed in solving directly a set of simultaneous equations by numerical iterations using a gradual inhibition method. Previously, an alternative solution was found by applying a Self-Consistent Monte Carlo (SCMC) method. The gradual inhibition method in an iterative procedure can give a more precise solution efficiently with fewer computational tasks than the SCMC method.

show abstract

Section: Introductionmentioning

confidence: 80%

Section: Cluster Learning Rulementioning

confidence: 99%

“…If we continue to present input patterns for a long duration much larger than the learning time constant, steady values of the synaptic connections will be achieved [14][15][16]:…”

Section: Steady State Of the Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Formation of an Orientation Preference Map - Gradual Inhibition Method

Inawashiro

Kuroiwa²,

Nakamura

et al. 2002

Neural Computing & Applications

View full text Add to dashboard Cite

show abstract

“…Though the information provided by optical imaging is significant, there seems to be no established theory explaining the geometric organization of orientation domains. Many theoretical studies have focused on self-organization of the orientation map (Linsker 1986;Tanaka 1990;Miller 1994;Obermayer et al 1992;Kuroiwa et al 2000), but few have focused on the geometric structure of the map. Here we consider geometrical characteristics of the orientation map before we go into the details of our model.…”

Section: Geometric Orientation Mapmentioning

confidence: 99%

An explanation of contextual modulation by short-range isotropic connections and orientation map geometry in the primary visual cortex

et al. 2004

View full text Add to dashboard Cite

Recent experimental studies on the primary visual cortex have revealed complicated nonclassical neuronal activities. Contextual modulation on orientation-contrast is one typical example of nonclassical neuronal behavior. This modulation by surrounding stimuli in a nonclassical receptive field is mainly thought to be mediated by short- and long-range horizontal connections within the primary visual cortex. Short-range connections are circularly symmetrical and relatively independent of orientation preferences, while long-range connections are patchy, asymmetrical, and orientation specific. Although this modulation can be explained by long-range specific connections qualitatively, recent studies suggest that long-range connections alone may be insufficient with respect to the balance between two types of connections. Here, in order to clarify the role of short-range connections in the process of contextual modulation, we propose a model of the primary visual cortex with isotropic short-range connections and a geometric orientation map. Computational simulations using the model have demonstrated that contextual modulation can be explained by short-range connections alone. This is due to the interaction between the spatial periodicity of orientation domains and the excitatory-inhibitory regions arising from the propagation of activities.

show abstract

Multiwinner feedforward self-organizing neural network with a distributed representation of information

Wada

2006

Electron. Comm. Jpn. Pt. III

View full text Add to dashboard Cite

In order to expand the range of application of various unique functions of the neural network, it is necessary to attempt hardware implementation of the model. The hardware implementations of models hitherto proposed have various problems due to the complexity of the algorithm. This paper aims at hardware implementation for easily implementing the neural network on a hardware model and proposes a layered structure model based on a simple multiwinner algorithm. The multiwinner algorithm is a competition algorithm based on the model of von der Malsburg, in which multiple neurons are able to become winners in each layer. In each layer, the neurons located in the neighborhood of the winner neuron perform learning by Hebbian rules, affected by interaction due to lateral coupling with a fixed coupling coefficient. The following experiment is presented. Learning is performed for bar patterns with six different directions. After that, when character patterns of 0 to 9 are presented, the winner neurons appear locally and distributed on the two‐dimensional plane, indicating that the feature information of the presented patterns is mapped onto the distributed representation. Then the directional response of the neuron is examined. As regards the spatial distribution of the response direction of the neuron, it is verified that a neuron having an orientation selectivity with gradually changing response direction is formed. This indicates that the distributed representation is achieved and that an orientation‐selective structure is formed in the proposed multiwinner algorithm, which can easily be implemented in hardware. © 2006 Wiley Periodicals, Inc. Electron Comm Jpn Pt 3, 89(12): 31–41, 2006; Published online in Wiley InterScience (http://www.interscience.wiley.com). DOI 10.1002/ecjc.20289

show abstract

Self-organization of orientation maps in a formal neuron model using a cluster learning rule

Cited by 7 publications

References 21 publications

Formation of an Orientation Preference Map - Gradual Inhibition Method

Formation of an Orientation Preference Map - Gradual Inhibition Method

An explanation of contextual modulation by short-range isotropic connections and orientation map geometry in the primary visual cortex

Multiwinner feedforward self-organizing neural network with a distributed representation of information

Contact Info

Product

Resources

About