Learning Algorithms Which Make Multilayer Neural Networks Multiple-Weight-and-Neuron-Fault Tolerant
スポンサーリンク
概要
- 論文の詳細を見る
Two simple but useful methods, called the deep learning methods, for making multilayer neural networks tolerant to multiple link-weight and neuron-output faults, are proposed. The methods make the output errors in learning phase smaller than those in practical use. The abilities of fault-tolerance of the multilayer neural networks in practical use, are analyzed in the relationship between the output errors in learning phase and in practical use. The analytical result shows that the multilayer neural networks have complete (100%) fault-tolerance to multiple weight-and-neuron faults in practical use. The simulation results concerning the rate of successful learnings, the ability of fault-tolerance, and the learning time, are also shown.
- （社）電子情報通信学会の論文
- 2008-04-01
著者
-
Mori Masatoshi
Department Of Information And Computer Science Polytechnic University
-
Takanami Itsuo
Department Of Electronics Engineering
-
Takanami Itsuo
Department Of Information And Computer Science Polytechnic University
-
Mori Masatoshi
Department Of Electronic Engineering Nagasaki University
-
HORITA Tadayoshi
Department of Information and Computer Science, Polytechnic University
-
Horita Tadayoshi
Department Of Information And Computer Science Polytechnic Univerity
-
Mori Masatoshi
Department Of Chest Surgery Ehime Prefectural Central Hospital
-
MORI Masatoshi
Department of Applied Chemistry, School of Engineering, Nagoya University
関連論文
- An algorithm for tower of hanoi with four or more poles
- A note on bottom-up pyramid acceptors
- Video file system
- A modified algorithm for taking reciprocal of n-bit integers
- Dip and Hump Type Quantum Oscillations in Magnetoacoustic Attenuation in Semimetals : II. LOW TEMPERATURE PROPERTIES OF SOLIDS : Metals and Semiconductors
- A note on multihead on-line turing machines
- Solitary fibrous tumors of the pleura presenting satellite tumors
- Some Anomalies in Magnetoacoustic Attenuation in Bismuth
- Anomalies in Giant Quantum Attenuation of Sound Waves in Bismuth at High Magnetic Fields. II. : Existence of Extra Attenuation Peaks
- Anomalies in Giant Quantum Attenuation of Sound Waves in Bismuth at High Magnetic Fields. I. : Temperature and Frequency Dependences
- Asymmetric Anionic Polymerization of 1-Phenyldibenzosuberyl and 1-(2-Pyridyl)dibenzosuberyl Methacrylates and Chiral Recognition Ability of the Obtained Polymers
- An Analysis for Fault-Tolerant 3D Processor Arrays Using 1.5-Track Switches
- An implementation of a fault-tolerant 2D systolic array on an FPGA and its evaluation (ディペンダブルコンピューティング)
- An Efficiently Self-Reconstructing Array System Using E-11/2-Track Switches(Fault Tolerance)
- A note on decision problems for three-way two-dimensional finite automata
- Learning Algorithms Which Make Multilayer Neural Networks Multiple-Weight-and-Neuron-Fault Tolerant
- Surgical Resection Following Induction Chemoradiotherapy for Locally Advanced Lung Cancer
- Tilt Deformation of Metalorganic Chemical Vapor Deposition Grown GaP on Si Substrate
- Some Anomalies in Magnetoacoustic Attenuation in Antimony at High Magnetic Fields