This paper compares the performances of three types of autoencoder neural networks, namely, the traditional autoencoder with Restricted Boltzmann Machine (RBM), the stacked autoencoder without RBM and the stacked auto...
详细信息
ISBN:
(纸本)9781424416424
This paper compares the performances of three types of autoencoder neural networks, namely, the traditional autoencoder with Restricted Boltzmann Machine (RBM), the stacked autoencoder without RBM and the stacked autoencoder with RBM based on the efficiency for reconstruction of handwritten digit images. Experiments are performed to determine the reconstruction error in all the three cases using the same architecture configuration and training algorithm. The results show that the RBM stacked autoencoder gives better performance in terms of the reconstruction error compared to the other two architectures. We also show that all the architectures outperform PCA in terms of the reconstruction error.
This paper presents techniques for image reconstruction and recognition using autoencoders. Experiments are conducted to compare the performances of three types of autoencoder neural networks based on their efficiency...
详细信息
This paper presents techniques for image reconstruction and recognition using autoencoders. Experiments are conducted to compare the performances of three types of autoencoder neural networks based on their efficiency of reconstruction and recognition. Reconstruction error and recognition rate are determined in all the three cases using the same architecture configuration and training algorithm. The results obtained with autoencoders are also compared with those obtained using principal component analysis method. Instead of whole images, image patches are used for training, and this leads to much simpler autoencoder architectures and reduced training time.
Automated document retrieval and classification is of central importance in many contexts;our main motivating goal is the efficient classification and retrieval of "interests" on the internet when only posit...
详细信息
Automated document retrieval and classification is of central importance in many contexts;our main motivating goal is the efficient classification and retrieval of "interests" on the internet when only positive information is available. In this paper, we show how a simple feed-forward neural network can be trained to filter documents under these conditions, and that this method seems to be superior to modified methods (modified to use only positive examples), such as Rocchio, Nearest Neighbor, Naive-Bayes, Distance-based Probability and One-Class SVM algorithms. A novel experimental finding is that retrieval is enhanced substantially in this context by carrying out a certain kind of uniform transformation ("Hadamard") of the information prior to the training of the network. (c) 2006 Published by Elsevier B.V.
Recently, a nonlinear dimension reduction technique, called autoencoder, had been proposed. It can efficiently carry out mappings in both directions between the original data and low-dimensional code space. However, a...
详细信息
ISBN:
(纸本)9781424409723
Recently, a nonlinear dimension reduction technique, called autoencoder, had been proposed. It can efficiently carry out mappings in both directions between the original data and low-dimensional code space. However, a single autoencoder commonly maps all data into a single subspace. If the original data set have remarkable different categories (for example, characters and handwritten digits), then only one autoencoder will not be efficient. To deal with the data of remarkable different categories, this paper proposes an Auto-Associative Neural Network System (AANNS) based on multiple autoencoders. The novel technique has the functions of auto-association, incremental learning and local update. Excitingly, these functions are the foundations of cognitive science. Experimental results on benchmark MNIST digit dataset and handwritten character-digit dataset show the advantages of the proposed model.
Recently, a nonlinear dimension reduction technique, called autoencoder, had been *** can efficiently carry out mappings in both directions between the original data and low-dimensional code ***, a single autoencoder ...
详细信息
Recently, a nonlinear dimension reduction technique, called autoencoder, had been *** can efficiently carry out mappings in both directions between the original data and low-dimensional code ***, a single autoencoder commonly maps all data into a single *** the original data set have remarkable different categories (for example, characters and handwritten digits), then only one autoencoder will not be efficient To deal with the data of remarkable different categories, this paper proposes an Auto-Associative Neural Network System (AANNS) based on multiple *** novel technique has the functions of auto-association, incremental learning and local ***, these functions are the foundations of cognitive *** results on benchmark MNIST digit dataset and handwritten character-digit dataset show the advantages of the proposed model.
We propose a model for a system with middle temporal neurons and medial superior temporal (MST) neurons by using a three-layered autoencoder. Noise effect is taken into account by using the framework of statistical ph...
详细信息
We propose a model for a system with middle temporal neurons and medial superior temporal (MST) neurons by using a three-layered autoencoder. Noise effect is taken into account by using the framework of statistical physics. We define a cost function of the autoencoder, from which a learning rule is derived by a gradient descent method, within a mean-field approximation. We find a pair of values of two noise levels at which a minimum value of the cost function is attained. We investigate response properties of the MST neurons to optical flows for various types of motion at the pair of optimal values of two noise levels. We obtain that the response properties of the MST neurons are similar to those obtained from neurophysiological experiments. (C) 2002 Elsevier Science B.V. All rights reserved.
This paper proposes a viewpoint invariant face recognition method in which several viewpoint dependent classifiers are combined by a gating network. The gating network is designed as autoencoder with competitive hidde...
详细信息
This paper proposes a viewpoint invariant face recognition method in which several viewpoint dependent classifiers are combined by a gating network. The gating network is designed as autoencoder with competitive hidden units. The viewpoint dependent representations of faces can be obtained by this autoencoder from many faces with different views. By using this autoencoder as the gating network in the mixture of experts (classifiers) architecture, the network can be self-organized such that one of the classifiers is selectively activated depending on the viewpoint of a given face image. Experimental results of view invariant face recognition are shown using the face images captured from different viewpoints. (C) 2002 Elsevier Science B.V. All rights reserved.
In the pharmaceutical industry, there are a variety of organizational and process approaches to coding and classifying patient delta. In any pharmaceutical development structure, automated coding of patient clinical d...
详细信息
In the pharmaceutical industry, there are a variety of organizational and process approaches to coding and classifying patient delta. In any pharmaceutical development structure, automated coding of patient clinical data greatly facilitates data analysis by reducing the amount of time spent on coding review. This paper will describe the clinical data encoding system currently in use at Astra Pharmaceuticals, L.P., and will present a portrait of a successful model for an autoencoding algorithm program. Computer-assisted coding cannot entirely substitute for coding and data review by qualified medical personnel;however a volume data autoencoding application can significantly improve the quality, consistency, and pace of the data coding process, thereby allowing for more efficient analysis and reporting in the execution of a clinical trial.
A generative neural network model, constrained by non-face examples chosen by an iterative algorithm, is applied to fact: detection. To improve the generalization ability of the model, another constraint based on the ...
详细信息
A generative neural network model, constrained by non-face examples chosen by an iterative algorithm, is applied to fact: detection. To improve the generalization ability of the model, another constraint based on the minimum description length is added. This model is tested and compared with another state-of-the-art face detection system on a large image test set collected at CMU.
This paper describes two new methods for modeling the manifolds of digitized images of handwritten digits. The models allow a priori information about the structure of the manifolds to be combined with empirical data....
详细信息
This paper describes two new methods for modeling the manifolds of digitized images of handwritten digits. The models allow a priori information about the structure of the manifolds to be combined with empirical data. Accurate modeling of the manifolds allows digits to be discriminated using the relative probability densities under the alternative models. One of the methods is grounded in principal components analysis, the other in factor analysis. Both methods are based on locally linear low-dimensional approximations to the underlying data manifold. Links with other methods that model the manifold are discussed.
暂无评论