Scene classification aims at grouping images into semantic categories. In this article, a new scene classification method is proposed. It consists of regularized auto-encoder-based feature learning step and SVM-based ...
详细信息
ISBN:
(纸本)9783662483657;9783662483633
Scene classification aims at grouping images into semantic categories. In this article, a new scene classification method is proposed. It consists of regularized auto-encoder-based feature learning step and SVM-based classification step. In the first step, the regularized auto-encoder, imposed with the maximum scatter difference (MSD) criterion and sparse constraint, is trained to extract features of the source images. In the second step, a multi-class SVM classifier is employed to classify those features. To evaluate the proposed approach, experiments based on 8-category sport events (LF data set) are conducted. Results prove that the introduced approach significantly improves the performance of the current popular scene classification methods.
Clustering single-cell RNA sequence (scRNA-seq) data poses statistical and computational challenges due to their high-dimensionality and data-sparsity, also known as 'dropout' events. Recently, regularized Aut...
详细信息
Clustering single-cell RNA sequence (scRNA-seq) data poses statistical and computational challenges due to their high-dimensionality and data-sparsity, also known as 'dropout' events. Recently, regularized auto-encoder (RAE) based deep neural network models have achieved remarkable success in learning robust low-dimensional representations. The basic idea in RAEs is to learn a non-linear mapping from the high-dimensional data space to a low-dimensional latent space and vice-versa, simultaneously imposing a distributional prior on the latent space, which brings in a regularization effect. This paper argues that RAEs suffer from the infamous problem of bias-variance trade-off in their naive formulation. While a simple AE wita latent regularization results in data over-fitting, a very strong prior leads to under-representation and thus bad clustering. To address the above issues, we propose a modified RAE framework (called the scRAE) for effective clustering of the single-cell RNA sequencing data. scRAE consists of deterministic AE with a flexibly learnable prior generator network, which is jointly trained with the AE. This facilitates scRAE to trade-off better between the bias and variance in the latent space. We demonstrate the efficacy of the proposed method through extensive experimentation on several real-world single-cell Gene expression datasets. The code for our work is available at https://***/arnabkmondal/scRAE.
Imbalanced learning is considered one of the challenging problems in machine learning. This problem arises when a learning algorithm is biased toward the majority class due to the large proportion of the majority clas...
详细信息
Imbalanced learning is considered one of the challenging problems in machine learning. This problem arises when a learning algorithm is biased toward the majority class due to the large proportion of the majority class data while detecting the minority class is of greater importance. In the present study, a novel method (MMRAE) is presented for imbalanced learning encompassing feature learning and classification steps. In the feature learning step, meaningful features are extracted from the minority data and their underlying manifold are captured by taking advantage of one-class learning approach through stacking two regularized auto-encoders. The existence of novel and different regularizers in each auto-encoder leads to a new representation with proper data discrimination which improves the between-class and within-class imbalanced problems. Then, in the classification step, the classification between the minority and majority class is performed by constructing a multilayer neural network using features learned throughout pre-training. The proposed method is extensively studied on six artificial and twenty real datasets in order to have a precise evaluation. Based on different criteria such as F-measure, G-mean, and AUC, the results represent considerable performance of the proposed method compared to several other existing methods.
暂无评论