The Experts below are selected from a list of 4869 Experts worldwide ranked by ideXlab platform

M Okada - One of the best experts on this subject based on the ideXlab platform.

  • online learning of a Simple Perceptron learning with margin
    Systems and Computers in Japan, 2004
    Co-Authors: K Hara, M Okada
    Abstract:

    The authors analyze the dynamics of online learning in a Simple Perceptron using a Gardner-style margin. The proposed method matches the Perceptron rules for a margin of κ = 0 and the Hebb rules when κ → ∞. The results of analysis show that the generalization error is smaller than that of the Perceptron rules and the Hebb rules during initial learning even though the proposed method is in between these two sets of learning rules. In addition, the authors show that the generalization error for the proposed method matches that of the Perceptron rules in terms of asymptotic characteristics. © 2004 Wiley Periodicals, Inc. Syst Comp Jpn, 35(7): 98–105, 2004; Published online in Wiley InterScience (). DOI 10.1002sscj.10473

  • on line learning through Simple Perceptron learning with a margin
    Neural Networks, 2004
    Co-Authors: K Hara, M Okada
    Abstract:

    Abstract We analyze a learning method that uses a margin κ a la Gardner for Simple Perceptron learning. This method corresponds to the Perceptron learning when κ=0, and to the Hebbian learning when κ→∞. Nevertheless, we found that the generalization ability of the method was superior to that of the Perceptron and the Hebbian methods at an early stage of learning. We analyzed the asymptotic property of the learning curve of this method through computer simulation and found that it was the same as for Perceptron learning. We also investigated an adaptive margin control method.

  • on line learning through Simple Perceptron with a margin
    arXiv: Disordered Systems and Neural Networks, 2003
    Co-Authors: K Hara, M Okada
    Abstract:

    We analyze a learning method that uses a margin $\kappa$ {\it a la} Gardner for Simple Perceptron learning. This method corresponds to the Perceptron learning when $\kappa=0$, and to the Hebbian learning when $\kappa \to \infty$. Nevertheless, we found that the generalization ability of the method was superior to that of the Perceptron and the Hebbian methods at an early stage of learning. We analyzed the asymptotic property of the learning curve of this method through computer simulation and found that it was the same as for Perceptron learning. We also investigated an adaptive margin control method.

  • on line learning trough Simple Perceptron learning with a margin
    International Conference on Neural Information Processing, 2002
    Co-Authors: K Hara, M Okada
    Abstract:

    We analyze a learning method that uses a margin k a la Gardner for Simple Perceptron learning. This method corresponds to Perceptron learning when k = 0, and to Hebbian learning when k /spl rarr/ /spl infin/. Nevertheless, we found that the generalization ability of the method was superior to that of the Perceptron and the Hebbian methods at an early stage of learning.

Karthik Soman - One of the best experts on this subject based on the ideXlab platform.

  • Image_1_A Model of Motion Processing in the Visual Cortex Using Neural Field With Asymmetric Hebbian Learning.TIF
    2019
    Co-Authors: Anila Gundavarapu, Srinivasa V. Chakravarthy, Karthik Soman
    Abstract:

    Neurons in the dorsal pathway of the visual cortex are thought to be involved in motion processing. The first site of motion processing is the primary visual cortex (V1), encoding the direction of motion in local receptive fields, with higher order motion processing happening in the middle temporal area (MT). Complex motion properties like optic flow are processed in higher cortical areas of the Medial Superior Temporal area (MST). In this study, a hierarchical neural field network model of motion processing is presented. The model architecture has an input layer followed by either one or cascade of two neural fields (NF): the first of these, NF1, represents V1, while the second, NF2, represents MT. A special feature of the model is that lateral connections used in the neural fields are trained by asymmetric Hebbian learning, imparting to the neural field the ability to process sequential information in motion stimuli. The model was trained using various traditional moving patterns such as bars, squares, gratings, plaids, and random dot stimulus. In the case of bar stimuli, the model had only a single NF, the neurons of which developed a direction map of the moving bar stimuli. Training a network with two NFs on moving square and moving plaids stimuli, we show that, while the neurons in NF1 respond to the direction of the component (such as gratings and edges) motion, the neurons in NF2 (analogous to MT) responding to the direction of the pattern (plaids, square object) motion. In the third study, a network with 2 NFs was simulated using random dot stimuli (RDS) with translational motion, and show that the NF2 neurons can encode the direction of the concurrent dot motion (also called translational flow motion), independent of the dot configuration. This translational RDS flow motion is decoded by a Simple Perceptron network (a layer above NF2) with an accuracy of 100% on train set and 90% on the test set, thereby demonstrating that the proposed network can generalize to new dot configurations. Also, the response properties of the model on different input stimuli closely resembled many of the known features of the neurons found in electrophysiological studies.

  • a model of motion processing in the visual cortex using neural field with asymmetric hebbian learning
    Frontiers in Neuroscience, 2019
    Co-Authors: Anila Gundavarapu, Srinivasa V. Chakravarthy, Karthik Soman
    Abstract:

    Neurons in the dorsal pathway of the visual cortex are thought to be involved in the motion processing. The first site of motion processing is the primary visual cortex (V1), encoding the direction of motion in local receptive fields, with global processing happening in the middle temporal area (MT). Complex motion properties like optic flow are processed in higher cortical areas of the Middle Superior Temporal area (MST). In this study, a hierarchical neural field network model of motion processing is presented. The model architecture has an input layer followed by either one or cascade of two neural fields (NF): the first of these, NF1, represents V1, while the second, NF2, represents MT. A special feature of the model is that lateral connections used in the neural fields are trained by asymmetric Hebbian learning, imparting to the neural field the ability to process sequential information in motion stimuli. The model was trained using various traditional moving patterns such as bars, squares, gratings, plaids, and random dot stimulus. In case of bar stimuli, the model had only a single NF, the neurons of which developed a direction map of the moving bar stimuli. Training a network with two NFs on moving square and moving plaids stimuli, we show that, while the neurons in NF1 respond to the direction of the component (such as gratings and edges) motion, the neurons in NF2 (analogous to MT) responding to the direction of the pattern (plaids, square object) motion. In the third study, a network with 2 NFs was simulated using random dot stimuli (RDS) with translational motion, and show that the NF2 neurons can encode the direction of the concurrent dot motion, independent of the dot configuration. This translational RDS flow motion is decoded by a Simple Perceptron network (a layer above NF2) with an accuracy of 100% on train set and 90% on the test set, thereby demonstrating that the proposed network can generalize to new dot configurations. Also, the response properties of the model on different input stimuli closely resembled many of the known features of the neurons found in electrophysiological studies.

  • Table_1_A Model of Motion Processing in the Visual Cortex Using Neural Field With Asymmetric Hebbian Learning.docx
    2019
    Co-Authors: Anila Gundavarapu, Srinivasa V. Chakravarthy, Karthik Soman
    Abstract:

    Neurons in the dorsal pathway of the visual cortex are thought to be involved in motion processing. The first site of motion processing is the primary visual cortex (V1), encoding the direction of motion in local receptive fields, with higher order motion processing happening in the middle temporal area (MT). Complex motion properties like optic flow are processed in higher cortical areas of the Medial Superior Temporal area (MST). In this study, a hierarchical neural field network model of motion processing is presented. The model architecture has an input layer followed by either one or cascade of two neural fields (NF): the first of these, NF1, represents V1, while the second, NF2, represents MT. A special feature of the model is that lateral connections used in the neural fields are trained by asymmetric Hebbian learning, imparting to the neural field the ability to process sequential information in motion stimuli. The model was trained using various traditional moving patterns such as bars, squares, gratings, plaids, and random dot stimulus. In the case of bar stimuli, the model had only a single NF, the neurons of which developed a direction map of the moving bar stimuli. Training a network with two NFs on moving square and moving plaids stimuli, we show that, while the neurons in NF1 respond to the direction of the component (such as gratings and edges) motion, the neurons in NF2 (analogous to MT) responding to the direction of the pattern (plaids, square object) motion. In the third study, a network with 2 NFs was simulated using random dot stimuli (RDS) with translational motion, and show that the NF2 neurons can encode the direction of the concurrent dot motion (also called translational flow motion), independent of the dot configuration. This translational RDS flow motion is decoded by a Simple Perceptron network (a layer above NF2) with an accuracy of 100% on train set and 90% on the test set, thereby demonstrating that the proposed network can generalize to new dot configurations. Also, the response properties of the model on different input stimuli closely resembled many of the known features of the neurons found in electrophysiological studies.

  • A Model of Motion Processing in the Visual Cortex Using Neural Field With Asymmetric Hebbian Learning
    Frontiers Media S.A., 2019
    Co-Authors: Anila Gundavarapu, Srinivasa V. Chakravarthy, Karthik Soman
    Abstract:

    Neurons in the dorsal pathway of the visual cortex are thought to be involved in motion processing. The first site of motion processing is the primary visual cortex (V1), encoding the direction of motion in local receptive fields, with higher order motion processing happening in the middle temporal area (MT). Complex motion properties like optic flow are processed in higher cortical areas of the Medial Superior Temporal area (MST). In this study, a hierarchical neural field network model of motion processing is presented. The model architecture has an input layer followed by either one or cascade of two neural fields (NF): the first of these, NF1, represents V1, while the second, NF2, represents MT. A special feature of the model is that lateral connections used in the neural fields are trained by asymmetric Hebbian learning, imparting to the neural field the ability to process sequential information in motion stimuli. The model was trained using various traditional moving patterns such as bars, squares, gratings, plaids, and random dot stimulus. In the case of bar stimuli, the model had only a single NF, the neurons of which developed a direction map of the moving bar stimuli. Training a network with two NFs on moving square and moving plaids stimuli, we show that, while the neurons in NF1 respond to the direction of the component (such as gratings and edges) motion, the neurons in NF2 (analogous to MT) responding to the direction of the pattern (plaids, square object) motion. In the third study, a network with 2 NFs was simulated using random dot stimuli (RDS) with translational motion, and show that the NF2 neurons can encode the direction of the concurrent dot motion (also called translational flow motion), independent of the dot configuration. This translational RDS flow motion is decoded by a Simple Perceptron network (a layer above NF2) with an accuracy of 100% on train set and 90% on the test set, thereby demonstrating that the proposed network can generalize to new dot configurations. Also, the response properties of the model on different input stimuli closely resembled many of the known features of the neurons found in electrophysiological studies

Katherine Morrison - One of the best experts on this subject based on the ideXlab platform.

  • fixed points of competitive threshold linear networks
    Neural Computation, 2019
    Co-Authors: Carina Curto, Jesse Geneson, Katherine Morrison
    Abstract:

    Threshold-linear networks (TLNs) are models of neural networks that consist of Simple, Perceptron-like neurons and exhibit nonlinear dynamics determined by the network's connectivity. The fixed poi...

  • fixed points of competitive threshold linear networks
    arXiv: Neurons and Cognition, 2018
    Co-Authors: Carina Curto, Jesse Geneson, Katherine Morrison
    Abstract:

    Threshold-linear networks (TLNs) are models of neural networks that consist of Simple, Perceptron-like neurons and exhibit nonlinear dynamics that are determined by the network's connectivity. The fixed points of a TLN, including both stable and unstable equilibria, play a critical role in shaping its emergent dynamics. In this work, we provide two novel characterizations for the set of fixed points of a competitive TLN: the first is in terms of a Simple sign condition, while the second relies on the concept of domination. We apply these results to a special family of TLNs, called combinatorial threshold-linear networks (CTLNs), whose connectivity matrices are defined from directed graphs. This leads us to prove a series of graph rules that enable one to determine fixed points of a CTLN by analyzing the underlying graph. Additionally, we study larger networks composed of smaller "building block" subnetworks, and prove several theorems relating the fixed points of the full network to those of its components. Our results provide the foundation for a kind of "graphical calculus" to infer features of the dynamics from a network's connectivity.

K Hara - One of the best experts on this subject based on the ideXlab platform.

  • online learning of a Simple Perceptron learning with margin
    Systems and Computers in Japan, 2004
    Co-Authors: K Hara, M Okada
    Abstract:

    The authors analyze the dynamics of online learning in a Simple Perceptron using a Gardner-style margin. The proposed method matches the Perceptron rules for a margin of κ = 0 and the Hebb rules when κ → ∞. The results of analysis show that the generalization error is smaller than that of the Perceptron rules and the Hebb rules during initial learning even though the proposed method is in between these two sets of learning rules. In addition, the authors show that the generalization error for the proposed method matches that of the Perceptron rules in terms of asymptotic characteristics. © 2004 Wiley Periodicals, Inc. Syst Comp Jpn, 35(7): 98–105, 2004; Published online in Wiley InterScience (). DOI 10.1002sscj.10473

  • on line learning through Simple Perceptron learning with a margin
    Neural Networks, 2004
    Co-Authors: K Hara, M Okada
    Abstract:

    Abstract We analyze a learning method that uses a margin κ a la Gardner for Simple Perceptron learning. This method corresponds to the Perceptron learning when κ=0, and to the Hebbian learning when κ→∞. Nevertheless, we found that the generalization ability of the method was superior to that of the Perceptron and the Hebbian methods at an early stage of learning. We analyzed the asymptotic property of the learning curve of this method through computer simulation and found that it was the same as for Perceptron learning. We also investigated an adaptive margin control method.

  • on line learning through Simple Perceptron with a margin
    arXiv: Disordered Systems and Neural Networks, 2003
    Co-Authors: K Hara, M Okada
    Abstract:

    We analyze a learning method that uses a margin $\kappa$ {\it a la} Gardner for Simple Perceptron learning. This method corresponds to the Perceptron learning when $\kappa=0$, and to the Hebbian learning when $\kappa \to \infty$. Nevertheless, we found that the generalization ability of the method was superior to that of the Perceptron and the Hebbian methods at an early stage of learning. We analyzed the asymptotic property of the learning curve of this method through computer simulation and found that it was the same as for Perceptron learning. We also investigated an adaptive margin control method.

  • on line learning trough Simple Perceptron learning with a margin
    International Conference on Neural Information Processing, 2002
    Co-Authors: K Hara, M Okada
    Abstract:

    We analyze a learning method that uses a margin k a la Gardner for Simple Perceptron learning. This method corresponds to Perceptron learning when k = 0, and to Hebbian learning when k /spl rarr/ /spl infin/. Nevertheless, we found that the generalization ability of the method was superior to that of the Perceptron and the Hebbian methods at an early stage of learning.

Anila Gundavarapu - One of the best experts on this subject based on the ideXlab platform.

  • Image_1_A Model of Motion Processing in the Visual Cortex Using Neural Field With Asymmetric Hebbian Learning.TIF
    2019
    Co-Authors: Anila Gundavarapu, Srinivasa V. Chakravarthy, Karthik Soman
    Abstract:

    Neurons in the dorsal pathway of the visual cortex are thought to be involved in motion processing. The first site of motion processing is the primary visual cortex (V1), encoding the direction of motion in local receptive fields, with higher order motion processing happening in the middle temporal area (MT). Complex motion properties like optic flow are processed in higher cortical areas of the Medial Superior Temporal area (MST). In this study, a hierarchical neural field network model of motion processing is presented. The model architecture has an input layer followed by either one or cascade of two neural fields (NF): the first of these, NF1, represents V1, while the second, NF2, represents MT. A special feature of the model is that lateral connections used in the neural fields are trained by asymmetric Hebbian learning, imparting to the neural field the ability to process sequential information in motion stimuli. The model was trained using various traditional moving patterns such as bars, squares, gratings, plaids, and random dot stimulus. In the case of bar stimuli, the model had only a single NF, the neurons of which developed a direction map of the moving bar stimuli. Training a network with two NFs on moving square and moving plaids stimuli, we show that, while the neurons in NF1 respond to the direction of the component (such as gratings and edges) motion, the neurons in NF2 (analogous to MT) responding to the direction of the pattern (plaids, square object) motion. In the third study, a network with 2 NFs was simulated using random dot stimuli (RDS) with translational motion, and show that the NF2 neurons can encode the direction of the concurrent dot motion (also called translational flow motion), independent of the dot configuration. This translational RDS flow motion is decoded by a Simple Perceptron network (a layer above NF2) with an accuracy of 100% on train set and 90% on the test set, thereby demonstrating that the proposed network can generalize to new dot configurations. Also, the response properties of the model on different input stimuli closely resembled many of the known features of the neurons found in electrophysiological studies.

  • a model of motion processing in the visual cortex using neural field with asymmetric hebbian learning
    Frontiers in Neuroscience, 2019
    Co-Authors: Anila Gundavarapu, Srinivasa V. Chakravarthy, Karthik Soman
    Abstract:

    Neurons in the dorsal pathway of the visual cortex are thought to be involved in the motion processing. The first site of motion processing is the primary visual cortex (V1), encoding the direction of motion in local receptive fields, with global processing happening in the middle temporal area (MT). Complex motion properties like optic flow are processed in higher cortical areas of the Middle Superior Temporal area (MST). In this study, a hierarchical neural field network model of motion processing is presented. The model architecture has an input layer followed by either one or cascade of two neural fields (NF): the first of these, NF1, represents V1, while the second, NF2, represents MT. A special feature of the model is that lateral connections used in the neural fields are trained by asymmetric Hebbian learning, imparting to the neural field the ability to process sequential information in motion stimuli. The model was trained using various traditional moving patterns such as bars, squares, gratings, plaids, and random dot stimulus. In case of bar stimuli, the model had only a single NF, the neurons of which developed a direction map of the moving bar stimuli. Training a network with two NFs on moving square and moving plaids stimuli, we show that, while the neurons in NF1 respond to the direction of the component (such as gratings and edges) motion, the neurons in NF2 (analogous to MT) responding to the direction of the pattern (plaids, square object) motion. In the third study, a network with 2 NFs was simulated using random dot stimuli (RDS) with translational motion, and show that the NF2 neurons can encode the direction of the concurrent dot motion, independent of the dot configuration. This translational RDS flow motion is decoded by a Simple Perceptron network (a layer above NF2) with an accuracy of 100% on train set and 90% on the test set, thereby demonstrating that the proposed network can generalize to new dot configurations. Also, the response properties of the model on different input stimuli closely resembled many of the known features of the neurons found in electrophysiological studies.

  • Table_1_A Model of Motion Processing in the Visual Cortex Using Neural Field With Asymmetric Hebbian Learning.docx
    2019
    Co-Authors: Anila Gundavarapu, Srinivasa V. Chakravarthy, Karthik Soman
    Abstract:

    Neurons in the dorsal pathway of the visual cortex are thought to be involved in motion processing. The first site of motion processing is the primary visual cortex (V1), encoding the direction of motion in local receptive fields, with higher order motion processing happening in the middle temporal area (MT). Complex motion properties like optic flow are processed in higher cortical areas of the Medial Superior Temporal area (MST). In this study, a hierarchical neural field network model of motion processing is presented. The model architecture has an input layer followed by either one or cascade of two neural fields (NF): the first of these, NF1, represents V1, while the second, NF2, represents MT. A special feature of the model is that lateral connections used in the neural fields are trained by asymmetric Hebbian learning, imparting to the neural field the ability to process sequential information in motion stimuli. The model was trained using various traditional moving patterns such as bars, squares, gratings, plaids, and random dot stimulus. In the case of bar stimuli, the model had only a single NF, the neurons of which developed a direction map of the moving bar stimuli. Training a network with two NFs on moving square and moving plaids stimuli, we show that, while the neurons in NF1 respond to the direction of the component (such as gratings and edges) motion, the neurons in NF2 (analogous to MT) responding to the direction of the pattern (plaids, square object) motion. In the third study, a network with 2 NFs was simulated using random dot stimuli (RDS) with translational motion, and show that the NF2 neurons can encode the direction of the concurrent dot motion (also called translational flow motion), independent of the dot configuration. This translational RDS flow motion is decoded by a Simple Perceptron network (a layer above NF2) with an accuracy of 100% on train set and 90% on the test set, thereby demonstrating that the proposed network can generalize to new dot configurations. Also, the response properties of the model on different input stimuli closely resembled many of the known features of the neurons found in electrophysiological studies.

  • A Model of Motion Processing in the Visual Cortex Using Neural Field With Asymmetric Hebbian Learning
    Frontiers Media S.A., 2019
    Co-Authors: Anila Gundavarapu, Srinivasa V. Chakravarthy, Karthik Soman
    Abstract:

    Neurons in the dorsal pathway of the visual cortex are thought to be involved in motion processing. The first site of motion processing is the primary visual cortex (V1), encoding the direction of motion in local receptive fields, with higher order motion processing happening in the middle temporal area (MT). Complex motion properties like optic flow are processed in higher cortical areas of the Medial Superior Temporal area (MST). In this study, a hierarchical neural field network model of motion processing is presented. The model architecture has an input layer followed by either one or cascade of two neural fields (NF): the first of these, NF1, represents V1, while the second, NF2, represents MT. A special feature of the model is that lateral connections used in the neural fields are trained by asymmetric Hebbian learning, imparting to the neural field the ability to process sequential information in motion stimuli. The model was trained using various traditional moving patterns such as bars, squares, gratings, plaids, and random dot stimulus. In the case of bar stimuli, the model had only a single NF, the neurons of which developed a direction map of the moving bar stimuli. Training a network with two NFs on moving square and moving plaids stimuli, we show that, while the neurons in NF1 respond to the direction of the component (such as gratings and edges) motion, the neurons in NF2 (analogous to MT) responding to the direction of the pattern (plaids, square object) motion. In the third study, a network with 2 NFs was simulated using random dot stimuli (RDS) with translational motion, and show that the NF2 neurons can encode the direction of the concurrent dot motion (also called translational flow motion), independent of the dot configuration. This translational RDS flow motion is decoded by a Simple Perceptron network (a layer above NF2) with an accuracy of 100% on train set and 90% on the test set, thereby demonstrating that the proposed network can generalize to new dot configurations. Also, the response properties of the model on different input stimuli closely resembled many of the known features of the neurons found in electrophysiological studies