检索结果-内蒙古大学图书馆

Lifted Bregman Training of Neural Networks

JOURNAL OF MACHINE LEARNING RESEARCH 2023年第1期24卷 1-51页

作者： Wang, Xiaoyu Benning, Martin Univ Cambridge Dept Appl Math & Theoret Phys Cambridge CB3 0WA England Queen Mary Univ London Sch Math Sci London E1 4NS England

We introduce a novel mathematical formulation for the training of feed-forward neural networks with (potentially non-smooth) proximal maps as activation functions. This formulation is based on Bregman distances and a key advantage is that its partial derivatives with respect to the network's parameters do not require the computation of derivatives of the network's activation functions. Instead of estimating the parameters with a combination of first-order optimisation method and back-propagation (as is the state-of-the-art), we propose the use of non-smooth first-order optimisation methods that exploit the specific structure of the novel formulation. We present several numerical results that demonstrate that these training approaches can be equally well or even better suited for the training of neural network-based classifiers and (denoising) autoencoders with sparse coding compared to more conventional training frameworks.

关键词： Lifted network training distributed optimisation Bregman distances sparse autoencoder denoising autoencoder classification compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Change detection based on deep feature representation and mapping transformation for multi-spatial-resolution remote sensing images

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2016年第Jun.期116卷 24-41页

作者： Zhang, Puzhao Gong, Maoguo Su, Linzhi Liu, Jia Li, Zhizhou Xidian Univ Key Lab Intelligent Percept & Image Understanding Minist Educ Int Res Ctr Intelligent Percept & Computat Xian 710071 Shaanxi Provinc Peoples R China

Multi-spatial-resolution change detection is a newly proposed issue and it is of great significance in remote sensing, environmental and land use monitoring, etc. Though multi-spatial-resolution image pair are two kinds of representations of the same reality, they are often incommensurable superficially due to their different modalities and properties. In this paper, we present a novel multi-spatial resolution change detection framework, which incorporates deep-architecture-based unsupervised feature learning and mapping-based feature change analysis. Firstly, we transform multi-resolution image-pair into the same pixel-resolution through co-registration, followed by details recovery, which is designed to remedy the spatial details lost in the registration. Secondly, the denoising autoencoder is stacked to learn local and high-level representation/feature from the local neighborhood of the given pixel, in an unsupervised fashion. Thirdly, motivated by the fact that multi-resolution image-pair share the same reality in the unchanged regions, we try to explore the inner relationships between them by building a mapping neural network. And it can be used to learn a mapping function based on the most-unlikely-changed feature-pairs, which are selected from all the feature-pairs via a coarse initial change map generated in advance. The learned mapping function can bridge the different representations and highlight changes. Finally, we can build a robust and contractive change map through feature similarity analysis, and the change detection result is obtained through the segmentation of the final change map. Experiments are carried out on four real datasets, and the results confirmed the effectiveness and superiority of the proposed method. (C) 2016 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Published by Elsevier B.V. All rights reserved.

关键词： Change detection Spatial-resolution denoising autoencoder Stacked denoising autoencoder Deep neural networks Feature transformation

来源：评论

学校读者我要写书评

暂无评论

A novel U-Net with dense block for drum signal separation from polyphonic music signal mixture

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2023年第3期17卷 627-633页

作者： George, E. Vinitha Devassia, V. P. Cochin Univ Sci & Technol Model Engn Coll Kochi Kerala India St Josephs Coll Engn & Technol Palai Kerala India

Deep neural network algorithms have shown promising results for music source signal separation. Most existing methods rely on deep networks, where billions of parameters need to be trained. In this paper, we propose a novel autoencoder framework with a reduced number of parameters to separate the drum signal component from a music signal mixture. A denoising autoencoder with a U-Net architecture and direct skip connections was employed. A dense block is included in the bottleneck of the autoencoder stage. This technique was tested on both demixing secret data (DSD) and the MUSDB database. The source-to-distortion ratio (SDR) for the proposed method was at par with that of other state-of-the-art methods, whereas the number of parameters required was quite low, making it computationally more efficient. The experiment performed using the proposed method to separate drum signal yielded an average SDR of 5.71 on DSD and 6.45 on MUSDB database while using only 0.32 million parameters.

关键词： Audio source separation Convolutional neural network Deep learning denoising autoencoder U-Net architecture

来源：评论

学校读者我要写书评

暂无评论

Robust Motion Planning for Multi-Robot Systems Against Position Deception Attacks

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2024年 19卷 2157-2170页

作者： Tang, Wenbing Zhou, Yuan Liu, Yang Ding, Zuohua Liu, Jing East China Normal Univ Shanghai Key Lab Trustworthy Comp Shanghai 200062 Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore Zhejiang Sci Tech Univ Sch Comp Sci & Technol Hangzhou 310018 Zhejiang Peoples R China

Deep reinforcement learning (DRL) is widely applied in motion planning for multi-robot systems as DRL leverages the offline training process to improve the real-time computation efficiency. In DRL-based methods, the DRL models compute an action for a robot based on the states of its surrounding obstacles, including other robots in the system. They always assume that the number of obstacles is fixed and the obtained obstacles' states are reliable. However, in the real world, a multi-robot system may suffer from various attacks, such as remote control attacks and network attacks, that cause wrong positions of the surrounding obstacles received by a robot. In this paper, we propose a robust motion planning method DAE-Crit-LSTM, integrating a denoising autoencoder (DAE) with DRL models, to mitigate such position deception attacks in environments with a different number of obstacles. DAE-Crit-LSTM shows the following two advantages. First, DAE-Crit-LSTM can be applied in benign and attacked scenarios and thus does not require any detector. It learns an encoder and a decoder to approximate the accurate positions of the obstacles, no matter under attack or not. Second, DAE-Crit-LSTM applies an LSTM (Long Short-Term Memory)-based DRL model to deal with a variable number of obstacles in the environment. It is worth noting that DAE-Crit-LSTM is method-agnostic and can be easily implemented in state-of-the-art motion planning methods. Comprehensive experiments show that DAE-Crit-LSTM can mitigate position deception attacks and guarantee safe motion. We also demonstrate the effectiveness and generalization of DAE-Crit-LSTM.

关键词： Planning Collision avoidance Multi-robot systems Robot sensing systems Sensors Detectors Computational modeling Deep reinforcement learning denoising autoencoder motion planning multi-robot systems position deception attacks

来源：评论

学校读者我要写书评

暂无评论

A deep learning approach to prediction of blood group antigens from genomic data

引用

TRANSFUSION 2024年第11期64卷 2179-2195页

作者： Moslemi, Camous Saekmose, Susanne Larsen, Rune Brodersen, Thorsten Bay, Jakob T. Didriksen, Maria Nielsen, Kaspar R. Bruun, Mie T. Dowsett, Joseph Dinh, Khoa M. Mikkelsen, Christina Hyvarinen, Kati Ritari, Jarmo Partanen, Jukka Ullum, Henrik Erikstrup, Christian Ostrowski, Sisse R. Olsson, Martin L. Pedersen, Ole B. Zealand Univ Hosp Dept Clin Immunol Koge Denmark Roskilde Univ Dept Sci & Environm Roskilde Denmark Copenhagen Univ Hosp Dept Clin Immunol Rigshop Copenhagen Denmark Aalborg Univ Hosp Dept Clin Immunol Aalborg Denmark Odense Univ Hosp Dept Clin Immunol Odense Denmark Aarhus Univ Hosp Dept Clin Immunol Aarhus Denmark Finnish Red Cross Blood Serv Helsinki Finland Statens Serum Inst Copenhagen Denmark Aarhus Univ Dept Clin Med Aarhus Denmark Univ Copenhagen Fac Hlth & Med Sci Dept Clin Med Copenhagen Denmark Lund Univ Dept Lab Med Lund Sweden Off Med Serv Dept Clin Immunol & Transfus Med Lund Sweden

Background: Deep learning methods are revolutionizing natural science. In this study, we aim to apply such techniques to develop blood type prediction models based on cheap to analyze and easily scalable screening array genotyping platforms. Methods: Combining existing blood types from blood banks and imputed screening array genotypes for similar to 111,000 Danish and 1168 Finnish blood donors, we used deep learning techniques to train and validate blood type prediction models for 36 antigens in 15 blood group systems. To account for missing genotypes a denoising autoencoder initial step was utilized, followed by a convolutional neural network blood type classifier. Results: Two thirds of the trained blood type prediction models demonstrated an F1-accuracy above 99%. Models for antigens with low or high frequencies like, for example, C-w, low training cohorts like, for example, Co-b, or very complicated genetic underpinning like, for example, RhD, proved to be more challenging for high accuracy (>99%) DL modeling. However, in the Danish cohort only 4 out of 36 models (Co-b, C-w, D-weak, Kp(a)) failed to achieve a prediction F1-accuracy above 97%. This high predictive performance was replicated in the Finnish cohort. Discussion: High accuracy in a variety of blood groups proves viability of deep learning-based blood type prediction using array chip genotypes, even in blood groups with nontrivial genetic underpinnings. These techniques are suitable for aiding in identifying blood donors with rare blood types by greatly narrowing down the potential pool of candidate donors before clinical grade confirmation.

关键词： AI blood antigen blood types convolutional neural network deep learning denoising autoencoder genetic prediction Illumina GSA

来源：评论

学校读者我要写书评

暂无评论

Breast cancer cell nuclei classification in histopathology images using deep neural networks

引用

INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY 2018年第2期13卷 179-191页

作者： Feng, Yangqin Zhang, Lei Yi, Zhang Sichuan Univ Coll Comp Sci Machine Intelligence Lab Chengdu 610065 Sichuan Peoples R China

Cell nuclei classification in breast cancer histopathology images plays an important role in effective diagnose since breast cancer can often be characterized by its expression in cell nuclei. However, due to the small and variant sizes of cell nuclei, and heavy noise in histopathology images, traditional machine learning methods cannot achieve desirable recognition accuracy. To address this challenge, this paper aims to present a novel deep neural network which performs representation learning and cell nuclei recognition in an end-to-end manner. The proposed model hierarchically maps raw medical images into a latent space in which robustness is achieved by employing a stacked denoising autoencoder. A supervised classifier is further developed to improve the discrimination of the model by maximizing inter-subject separability in the latent space. The proposed method involves a cascade model which jointly learns a set of nonlinear mappings and a classifier from the given raw medical images. Such an on-the-shelf learning strategy makes obtaining discriminative features possible, thus leading to better recognition performance. Extensive experiments with benign and malignant breast cancer datasets are conducted to verify the effectiveness of the proposed method. Better performance was obtained when compared with other feature extraction methods, and higher recognition rate was achieved when compared with other seven classification methods. We propose an end-to-end DNN model for cell nuclei and non-nuclei classification of histopathology images. It demonstrates that the proposed method can achieve promising performance in cell nuclei classification, and the proposed method is suitable for the cell nuclei classification task.

关键词： Cell nuclei classification Deep neural network denoising autoencoder Medical image processing Representation learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Context-Aware Recommendation Using Trust-Based Contextual Attentive autoencoder

引用

NEURAL PROCESSING LETTERS 2023年第5期55卷 6843-6864页

作者： Abinaya, S. Alphonse, A. Sherly Abirami, S. Kavithadevi, M. K. Vellore Inst Technol Sch Comp Sci & Engn Chennai Tamil Nadu India Thiagarajar Coll Engn Dept Comp Sci & Engn Madurai Tamil Nadu India

Context-aware recommender systems are intended primarily to consider the circumstances under which a user encounters an item to provide better-personalized recommendations. Users acquire point-of-interest, movies, products, and various online resources as suggestions. Classical collaborative filtering algorithms are shown to be satisfactory in a variety of recommendation activities processes, but cannot often capture complicated interactions between item and user, along with sparsity and cold start constraints. Hence it becomes a surge to apply a deep learning-based recommender model owing to its dynamic modeling potential and sustained success in other fields of application. In this work, a trust-based attentive contextual denoising autoencoder (TACDA) for enhanced Top-N context-aware recommendation is proposed. Specifically, the TCADA model takes the sparse preference of the user that is integrated with trust data as input into the autoencoder to prevail over the cold start and sparsity obstacle and efficiently accumulates the context condition into the model via attention framework. Thereby, the attention technique is used to encode context features into a latent space of the user's trust data that is integrated with their preferences, which interconnects personalized context circumstances with the active user's choice to deliver recommendations suited to that active user. Experiments conducted on Epinions, Caio, and LibraryThing datasets make it obvious the efficiency of the TACDA model persistently outperforms the state-of-the-art methods.

关键词： Social networks Attention mechanism denoising autoencoder Context-aware recommendations

来源：评论

学校读者我要写书评

暂无评论

Dynamic deep learning algorithm based on incremental compensation for fault diagnosis model

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS 2018年第1期11卷 846-860页

作者： Liu, Jing An, Yacheng Dou, Runliang Ji, Haipeng Hebei Univ Technol Sch Comp Sci & Engn Tianjin 300401 Peoples R China Hebei Key Lab Dig Dta Calculat Tianjin 300401 Peoples R China Univ Iowa Engn Sch Iowa City IA 52246 USA Tianjin Univ Coll Management & Econ Tianjin 300072 Peoples R China Hebei Univ Technol Res Inst Energy Equipment Mat Tianjin 300401 Peoples R China

As one of research and practice hotspots in the field of intelligent manufacturing, the machine learning approach is applied to diagnose and predict equipment fault for running state data. Despite deep learning approach overcomes the problem that the traditional machine learning approaches for fault diagnosis is difficult to characterize the complex mapping between the massive fault data, the exponentially grown and newly generated data is learned repeatedly, and these approaches cannot incrementally correct the model to adapt the situation that the states and properties of equipment are changed over time, resulting in the increase of time costs and the decrease of diagnosis accuracy of model. In this paper, a dynamic deep learning algorithm based on incremental compensation is proposed. Firstly, the feature modes of the newly generated data are extracted by using deep learning algorithm;it is then compared with the fault modes extracted from the historical data. Next, a similarity computing model is presented to dynamically adjust the weights of incrementally merged modes. Finally, the SVM algorithm is employed to classify the weighted modes by supervised way, and the BP algorithm utilized to fine tune the model, in order to complete the dynamic and compensatory adjustment of deep learning with original modes and incremental modes. The experimental results of bearing running data demonstrate that the proposed approach could significantly improve the accuracy of diagnosis and save the time cost, contributing to meet the varied needs of the real- time equipment fault diagnosis.

关键词： Deep learning Dynamic compensation Fault diagnosis denoising autoencoder Incremental learning

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised learning of the electronic health record for phenotype stratification

引用

JOURNAL OF BIOMEDICAL INFORMATICS 2016年 64卷 168-178页

作者： Beaulieu-Jones, Brett K. Greene, Casey S. Univ Penn Perelman Sch Med Grad Grp Genom & Computat Biol Philadelphia PA 19104 USA Univ Penn Perelman Sch Med Inst Biomed Informat Philadelphia PA 19104 USA Univ Penn Perelman Sch Med Dept Syst Pharmacol & Translat Therapeut Philadelphia PA 19104 USA Univ Penn Perelman Sch Med Inst Translat Med & Therapeut Philadelphia PA 19104 USA

Patient interactions with health care providers result in entries to electronic health records (EHRs). EHRs were built for clinical and billing purposes but contain many data points about an individual. Mining these records provides opportunities to extract electronic phenotypes, which can be paired with genetic data to identify genes underlying common human diseases. This task remains challenging: high quality phenotyping is costly and requires physician review;many fields in the records are sparsely filled;and our definitions of diseases are continuing to improve over time. Here we develop and evaluate a semi supervised learning method for EHR phenotype extraction using denoising autoencoders for phenotype stratification. By combining denoising autoencoders with random forests we find classification improvements across multiple simulation models and improved survival prediction in ALS clinical trial data. This is particularly evident in cases where only a small number of patients have high quality phenotypes, a common scenario in EHR-based research. denoising autoencoders perform dimensionality reduction enabling visualization and clustering for the discovery of new subtypes of disease. This method represents a promising approach to clarify disease subtypes and improve genotype-phenotype association studies that leverage EHRs. (C) 2016 The Author(s). Published by Elsevier Inc.

关键词： Electronic health record denoising autoencoder Unsupervised Electronic phenotyping Patient stratification Disease subtyping

来源：评论

学校读者我要写书评

暂无评论

Transport Analysis of Infinitely Deep Neural Network

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2019年第1期20卷 31-82页

作者： Sonoda, Sho Murata, Noboru RIKEN Ctr Adv Intelligence Project Chuo Ku 1-4-1 Nihonbashi Tokyo 1030027 Japan Waseda Univ Sch Adv Sci & Engn Shinjuku Ku 3-4-1 Okubo Tokyo 1698555 Japan

We investigated the feature map inside deep neural networks (DNNs) by tracking the transport map. We are interested in the role of depth - why do DNNs perform better than shallow models? - and the interpretation of DNNs- what do intermediate layers do? Despite the rapid development in their application, DNNs remain analytically unexplained because the hidden layers are nested and the parameters are not faithful. Inspired by the integral representation of shallow NNs, which is the continuum limit of the width, or the hidden unit number, we developed the flow representation and transport analysis of DNNs. The flow representation is the continuum limit of the depth, or the hidden layer number, and it is specified by an ordinary differential equation ( ODE) with a vector field. We interpret an ordinary DNN as a transport map or an Euler broken line approximation of the flow. Technically speaking, a dynamical system is a natural model for the nested feature maps. In addition, it opens a new way to the coordinate-free treatment of DNNs by avoiding the redundant parametrization of DNNs. Following Wasserstein geometry, we analyze a flow in three aspects: dynamical system, continuity equation, and Wasserstein gradient flow. A key finding is that we specified a series of transport maps of the denoising autoencoder (DAE), which is a cornerstone for the development of deep learning. Starting from the shallow DAE, this paper develops three topics: the transport map of the deep DAE, the equivalence between the stacked DAE and the composition of DAEs, and the development of the double continuum limit or the integral representation of the flow representation. As partial answers to the research questions, we found that deeper DAEs converge faster and the extracted features are better;in addition, a deep Gaussian DAE transports mass to decrease the Shannon entropy of the data distribution. We expect that further investigations on these questions lead to the development of an interpre

关键词： representation learning denoising autoencoder flow representation continuum limit backward heat equation Wasserstein geometry ridgelet analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：