PROBLEM OF RANK-DEFICIENCIES OF A JACOBEAN FOR A NEURAL NETWORK
スポンサーリンク
概要
- 論文の詳細を見る
The problem of estimating the parameters in Artificial Neural Networks is mostly seen as one of nonlinear parameter estimation. Several training algorithms, for setting the parameters, use the steepest descent methods and their variants. Unfortunately, in many cases, due to an insufficient number of learning samples, the training problems are underdetermined. Analogously, an inappropriately selected training set may cause rank-deficiencies of not only the resulting mapping, but also of its principal submappings. Due to such problem of rank-deficiencies, the search direction for iterative steepest descent and conjugate gradient techniques is incomplete and training algorithms indicate slow convergence or, in the worst cases, they fall to find minima. In this paper we show the existence of a minimum training set, T_<min>, such that Jacobeans of all the principal submappings are of maximum rank and the Jacobean of the resulting mapping, F, has a full rank.
- 社団法人電子情報通信学会の論文
- 1995-12-09
著者
-
Usui Shiro
Deparment Of Information And Computer Sciences Toyohashi University Of Technology
-
Geczy Peter
Department Of Information And Computer Sciences Toyohashi University Of Technology
関連論文
- Mathematical model study of continuous transmitter release in the synaptic terminal of goldfish retinal bipolar cells
- ELECTRICAL INTERACTIONS BETWEEN THE SINOATRIAL NODE AND ATRIAL MUSCLE THROUGH AN EXTERNAL CIRCUIT
- INHOMOGENEOUS CELLULAR ACTIVATION TIME AND Vmax IN NORMAL MYOCARDIAL TISSUE UNDER ELECTRICAL FIELD STIMULATION WITH A LOW POTENTIAL GRADIENT
- On the Statistical Properties of Least Squares Estimators of Layered Neural Networks
- Upper bound of the expected training error of neural network regression for a Gaussian noise sequence
- Dynamic Sample Selection : Theory
- Desensitization of the GABA_A Receptor Shifts the Dynamic Range of Retinal Horizontal Cells Due to Light and Dark Adaptation
- Ionic current model of rabbit retinal horizontal cell
- Sample Selection Algorithm Utilizing Lipschitz Continuity Condition
- RULE EXTRACTION FROM TRAINED ARTIFICAL NEURAL NETWORKS
- Dynamic Sample Selection: Implementation
- PROBLEM OF RANK-DEFICIENCIES OF A JACOBEAN FOR A NEURAL NETWORK
- Color Discrimination Mechanisms Mediating Visual Search