A Multiobjective Sparse Feature Learning Model for Deep Neural Networks

Gong Maoguo; Liu Jia; Li Hao; Cai Qing; Su Linzhi

首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >A Multiobjective Sparse Feature Learning Model for Deep Neural Networks

【24h】

A Multiobjective Sparse Feature Learning Model for Deep Neural Networks

机译：深度神经网络的多目标稀疏特征学习模型

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Hierarchical deep neural networks are currently popular learning models for imitating the hierarchical architecture of human brain. Single-layer feature extractors are the bricks to build deep networks. Sparse feature learning models are popular models that can learn useful representations. But most of those models need a user-defined constant to control the sparsity of representations. In this paper, we propose a multiobjective sparse feature learning model based on the autoencoder. The parameters of the model are learnt by optimizing two objectives, reconstruction error and the sparsity of hidden units simultaneously to find a reasonable compromise between them automatically. We design a multiobjective induced learning procedure for this model based on a multiobjective evolutionary algorithm. In the experiments, we demonstrate that the learning procedure is effective, and the proposed multiobjective model can learn useful sparse features.

机译：分层深度神经网络是当前流行的用于模仿人脑分层体系结构的学习模型。单层特征提取器是构建深度网络的基础。稀疏特征学习模型是可以学习有用表示的流行模型。但是这些模型中的大多数都需要一个用户定义的常数来控制表示的稀疏性。本文提出了一种基于自动编码器的多目标稀疏特征学习模型。通过同时优化两个目标（重构误差和隐藏单元的稀疏性）以自动找到它们之间的合理折衷，可以学习模型的参数。我们基于多目标进化算法为此模型设计了一个多目标诱导学习程序。在实验中，我们证明了学习过程是有效的，并且所提出的多目标模型可以学习有用的稀疏特征。

著录项

来源
《Neural Networks and Learning Systems, IEEE Transactions on》 |2015年第12期|3263-3277|共15页
作者
Gong Maoguo; Liu Jia; Li Hao; Cai Qing; Su Linzhi;
展开▼
作者单位

Key Laboratory of Intelligent Perception and Image Understanding, International Research Center for Intelligent Perception and Computation, Ministry of Education, Xidian University, Xi’an, China;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Deep neural networks; evolutionary algorithm; multiobjective optimization; sparse feature learning; sparse feature learning.;

机译：深度神经网络;进化算法;多目标优化;稀疏特征学习;稀疏特征学习。;

相似文献

外文文献
中文文献
专利

1. Deep Region of Interest and Feature Extraction Models for Palmprint Verification Using Convolutional Neural Networks Transfer Learning [J] . Mahdieh Izadpanahkakhk, Seyyed Mohammad Razavi, Mehran Taghipour-Gorjikolaie, Applied Sciences . 2018,第7期

机译：使用卷积神经网络转移学习进行掌纹验证的深层感兴趣区域和特征提取模型
2. DEEP NEURAL NETWORKS FOR IRIS RECOGNITION SYSTEM BASED ON VIDEO: STACKED SPARSE AUTO ENCODERS (SSAE) AND BI-PROPAGATION NEURAL NETWORK MODELS [J] . ASAMA KUDER NSEAF, AZIZAH JAAFAR, KHIDER NASSIF JASSIM, Journal of Theoretical and Applied Information Technology . 2016,第2期

机译：基于视频的虹膜识别系统深层神经网络：堆叠稀疏自动编码器（SSAE）和双向传播神经网络模型
3. Deep neural networks compression learning based on multiobjective evolutionary algorithms [J] . Huang Junhao, Sun Weize, Huang Lei Neurocomputing . 2020,第Feba22期

机译：基于多目标进化算法的深度神经网络压缩学习
4. FPGA Design of Efficient Kidney Image Classification using Algebric Histogram Feature Model and Sparse Deep Neural Network (SDNN) Techniques [C] . R. Vinoth, K. Bommannaraja Conference on Emerging Devices and Smart Systems . 2017

机译：使用代数直方图特征模型和稀疏深神经网络（SDNN）技术的高效肾图像分类设计的FPGA设计
5. Prediction of Electronic Component Prices:from Classical Statistical and Machine Learning Models to Deep Neural Networks with Feature Embedding [D] . Zhang, Yu. 2019

机译：电子零件价格的预测：从经典的统计和机器学习模型到具有特征嵌入的深度神经网络
6. A Deep Learning Model for Fault Diagnosis with a Deep Neural Network and Feature Fusion on Multi-Channel Sensory Signals [O] . Qing Ye, Shaohu Liu, Changhua Liu 2020

机译：深度神经网络故障诊断的深度学习模型多通道感觉信号的特征融合
7. Multi-View Deep Network: A Deep Model Based on Learning Features From Heterogeneous Neural Networks for Sentiment Analysis [O] . Hossein Sadr, Mir Mohsen Pedram, Mohammad Teshnehlab 2020

机译：多视图深网络：基于异构神经网络情感分析的深度模型

A Multiobjective Sparse Feature Learning Model for Deep Neural Networks

摘要

著录项

相似文献

相关主题

期刊订阅