Statistical Mechanics of On-line Node-perturbation Learning

スポンサーリンク

概要

• 論文の詳細を見る

• Node-perturbation learning (NP-learning) is a kind of statistical gradient descent algorithm that estimates the gradient of an objective function through application of a small perturbation to the outputs of the network. It can be applied to problems where the objective function is not explicitly formulated, including reinforcement learning. In this paper, we show that node-perturbation learning can be formulated as on-line learning in a linear perceptron with noise, and we can derive the differential equations of order parameters and the generalization error in the same way as for the analysis of learning in a linear perceptron through statistical mechanical methods. From analytical results, we show that cross-talk noise, which originates in the error of the other outputs, increases the generalization error as the output number increases.

著者

• Okanoya Kazuo

  Brain Science Institute Riken

• Hara Kazuyuki

  College Of Industrial Technology Nihon University

• KATAHIRA KENTARO

  Japan Science Technology Agency, ERATO Okanoya Emotional Information Project

• Okada Masato

  Graduate School Of Engineering Science Osaka University

• Katahira Kentaro

  Japan Science and Technology Agency, ERATO Okanoya Emotional Information Project, Wako, Saitama 351-0198, Japan

• Okanoya Kazuo

  Brain Science Institute, RIKEN

• Hara Kazuyuki

  College of Industrial Technology, Nihon University

関連論文

• Statistical Mechanics of On-Line Node-Perturbation Learning
• Statistical Mechanical Study of Code-Division Multiple-Access Multiuser Detectors : Analysis of Replica Symmetric and One-Step Replica Symmetry Breaking Solutions(General)
• Statistical Mechanical Analysis of CDMA Multiuser Detectors : AT Stability and Entropy of the RS Solution, and 1RSB Solution
• Retrieval Property of Attractor Network with Synaptic Depression(General)
• Analysis of Ensemble Learning Using Simple Perceptrons Based on Online Learning Theory
• Retrieval of Branching Sequences in an Associative Memory Model with Common External Input and Bias Input(Cross-disciplinary physics and related areas of science and technology)
• Residual Energies after Slow Quantum Annealing(General)
• Multiple Stability of a Sparsely Encoded Attractor Neural Network Model for the Inferior Temporal Cortex(General)
• Image Restoration with a Truncated Gaussian Model(General)
• Statistical Mechanics of On-line Node-perturbation Learning
• Ensemble Learning of Linear Perceptrons : On-Line Learning Theory(General)
• Analysis of XY Model with Mexican-Hat Interaction on a Circle
• Exact Inference in Discontinuous Firing Rate Estimation Using Belief Propagation
• Influence of Synaptic Depression on Memory Storage Capacity
• Neural Network Model of Spatial Memory: Associative Recall of Maps
• Statistical Mechanics of On-Line Mutual Learning with Many Linear Perceptrons
• Statistical Mechanics of Mutual Learning with a Latent Teacher(General)
• Mean Field Analysis of Stochastic Neural Network Models with Synaptic Depression
• Rate Reduction for Associative Memory Model n Hodgkin-Huxley-Type Network(Cross-disciplinary physics and related areas of science and technology)
• Higher Order Effects on Rate Reduction for Networks of Hodgkin-Huxley Neurons(Cross-disciplinary physics and related areas of science and technology)
• Estimation of Intracellular Calcium Ion Concentration by Nonlinear State Space Modeling and Expectation-Maximization Algorithm for Parameter Estimation
• Neural Network Model with Discrete and Continuous Information Representation
• Estimating Membrane Resistance over Dendrite Using Markov Random Field
• Stability Analysis of Stochastic Neural Network with Depression and Facilitation Synapses
• Analysis of XY Model with Mexican-Hat Interaction on a Circle ---Derivation of Saddle Point Equations and Study of Bifurcation Structure---
• Statistical Mechanics of On-line Ensemble Teacher Learning through a Novel Perceptron Learning Rule
• Solvable Model of a Phase Oscillator Network on a Circle with Infinite-Range Mexican-Hat-Type Interaction
• Multiple Stability of a Sparsely Encoded Attractor Neural Network Model for the Inferior Temporal Cortex
• Image Segmentation and Restoration Using Switching State-Space Model and Variational Bayesian Method
• Statistical Mechanical Analysis of CDMA Multiuser Detectors : AT Stability and Entropy of the RS Solution, and 1RSB Solution
• Stability Analysis of Attractor Neural Network Model of Inferior Temporal Cortex —Relationship between Attractor Stability and Learning Order—
• Bayesian Image Restoration for Medical Images Using Radon Transform
• Statistical Mechanics of Mexican-Hat-Type Horizontal Connection
• Statistical Mechanics of Node-Perturbation Learning for Nonlinear Perceptron
• Inter-Layer Correlation in a Feed-Forward Network with Intra-Layer Common Noise
• Continuous Attractor that Appears in Autoassociative Memory Model Extended to XY Spin System
• Statistical–Mechanical Analysis of Attractor Dynamics in a Hysteretic Neuron Network
• A Numerical Analysis of Learning Coefficient in Radial Basis Function Network
• Theoretical Analysis of Learning Speed in Gradient Descent Algorithm Replacing Derivative with Constant
• Inter-Layer Correlation in a Feed-Forward Network with Intra-Layer Common Noise
• Analysis of Ensemble Learning Using Simple Perceptrons Based on Online Learning Theory

もっと見る 閉じる

スポンサーリンク