1 O ct 1 99 9 Categorization in fully connected multi - state neural network models
نویسندگان
چکیده
The categorization ability of fully connected neural network models, with either discrete or continuous Q-state units, is studied in this work in replica symmetric mean-field theory. Hierarchically correlated multi-state patterns in a two level structure of ancestors and descendents (examples) are embedded in the network and the categorization task consists in recognizing the ancestors when the network is trained exclusively with their descendents. Explicit results for the dependence of the equilibrium properties of a Q = 3-state model and a Q = ∞-state model are obtained in the form of phase diagrams and categorization curves. A strong improvement of the categorization ability is found when the network is trained with examples of low activity. The cate-gorization ability is found to be robust to finite threshold and synaptic noise. The Almeida-Thouless lines that limit the validity of the replica-symmetric results, are also obtained.
منابع مشابه
Estimation of Network Reliability for a Fully Connected Network with Unreliable Nodes and Unreliable Edges using Neuro Optimization
In this paper it is tried to estimate the reliability of a fully connected network of some unreliable nodes and unreliable connections (edges) between them. The proliferation of electronic messaging has been witnessed during the last few years. The acute problem of node failure and connection failure is frequently encountered in communication through various types of networks. We know that a ne...
متن کاملCategorization in fully connected multistate neural network models.
The categorization ability of fully connected neural network models, with either discrete or continuous Q-state units, is studied in this work in replica symmetric mean-field theory. Hierarchically correlated multistate patterns in a two level structure of ancestors and descendents (examples) are embedded in the network and the categorization task consists in recognizing the ancestors when the ...
متن کاملHolistic Interstitial Lung Disease Detection using Deep Convolutional Neural Networks: Multi-label Learning and Unordered Pooling
Accurately predicting and detecting interstitial lung disease (ILD) patterns given any computed tomography (CT) slice without any pre-processing prerequisites, such as manually delineated regions of interest (ROIs), is a clinically desirable, yet challenging goal. The majority of existing work relies on manuallyprovided ILD ROIs to extract sampled 2D image patches from CT slices and, from there...
متن کاملModeling the Intra-class Variability for Liver Lesion Detection Using a Multi-class Patch-Based CNN
Automatic detection of liver lesions in CT images poses a great challenge for researchers. In this work we present a deep learning approach that models explicitly the variability within the non-lesion class ,based on prior knowledge of the data, to support an automated lesion detection system. A multi-class convolutional neural network (CNN) is proposed to categorize input image patches into su...
متن کاملar X iv : h ep - l at / 9 91 00 01 v 1 1 O ct 1 99 9 1 Flavor Singlet Axial Coupling of the Proton – An Updated Analysis ∗
We present a combined analysis of SESAM and T χL data for the flavor singlet axial coupling G 1 A of the proton, which is very helpful to stabilize the disconnected signals at small quark masses. From connected and disconnected contributions we use the tadpole improved renormalization constant ZA and obtain G 1 A = 0.21(12).
متن کامل