Open Access. Powered by Scholars. Published by Universities.®

Physical Sciences and Mathematics Commons™

Open Access. Powered by Scholars. Published by Universities.®

Deep learning

Discipline
Institution
Publication Year
Publication
Publication Type
File Type

Articles 871 - 890 of 890

Full-Text Articles in Physical Sciences and Mathematics

Conditional Computation In Deep And Recurrent Neural Networks, Andrew Scott Davis Aug 2016

Conditional Computation In Deep And Recurrent Neural Networks, Andrew Scott Davis

Doctoral Dissertations

Recently, deep learning models such as convolutional and recurrent neural networks have displaced state-of-the-art techniques in a variety of application domains. While the computationally heavy process of training is usually conducted on powerful graphics processing units (GPUs) distributed in large computing clusters, the resulting models can still be somewhat heavy, making deployment in resource- constrained environments potentially problematic. In this work, we build upon the idea of conditional computation, where the model is given the capability to learn how to avoid computing parts of the graph. This allows for models where the number of parameters (and in a sense, the …

Go to article

Protein Residue-Residue Contact Prediction Using Stacked Denoising Autoencoders, Joseph Bailey Luttrell Iv Aug 2016

Protein Residue-Residue Contact Prediction Using Stacked Denoising Autoencoders, Joseph Bailey Luttrell Iv

Honors Theses

Protein residue-residue contact prediction is one of many areas of bioinformatics research that aims to assist researchers in the discovery of structural features of proteins. Predicting the existence of such structural features can provide a starting point for studying the tertiary structures of proteins. This has the potential to be useful in applications such as drug design where tertiary structure predictions may play an important role in approximating the interactions between drugs and their targets without expending the monetary resources necessary for preliminary experimentation. Here, four different methods involving deep learning, support vector machines (SVMs), and direct coupling analysis were …

Go to article

Deep Semantic Image Interpolation, Joshua D. Little Jul 2016

Deep Semantic Image Interpolation, Joshua D. Little

McKelvey School of Engineering Theses & Dissertations

Image datasets often live on a continuum: Images from an outdoor scene vary from day to night, across different weather conditions, and over the course of seasons. Faces age and exhibit different expressions. We consider the problem of taking individual images from these datasets and explicitly manipulating those images to change where they lie on the continuum. We focus on a version of this problem that requires as little input as possible, and we build off of previous work using CNN features to construct an intermediate image manifold on which to manipulate the images. We also investigate a novel way …

Go to article

Machine Learning Methods For Medical And Biological Image Computing, Rongjian Li Jul 2016

Machine Learning Methods For Medical And Biological Image Computing, Rongjian Li

Computer Science Theses & Dissertations

Medical and biological imaging technologies provide valuable visualization information of structure and function for an organ from the level of individual molecules to the whole object. Brain is the most complex organ in body, and it increasingly attracts intense research attentions with the rapid development of medical and bio-logical imaging technologies. A massive amount of high-dimensional brain imaging data being generated makes the design of computational methods for efficient analysis on those images highly demanded. The current study of computational methods using hand-crafted features does not scale with the increasing number of brain images, hindering the pace of scientific discoveries …

Go to article

Machine Learning Methods For Brain Image Analysis, Ahmed Fakhry Jul 2016

Machine Learning Methods For Brain Image Analysis, Ahmed Fakhry

Computer Science Theses & Dissertations

Understanding how the brain functions and quantifying compound interactions between complex synaptic networks inside the brain remain some of the most challenging problems in neuroscience. Lack or abundance of data, shortage of manpower along with heterogeneity of data following from various species all served as an added complexity to the already perplexing problem. The ability to process vast amount of brain data need to be performed automatically, yet with an accuracy close to manual human-level performance. These automated methods essentially need to generalize well to be able to accommodate data from different species. Also, novel approaches and techniques are becoming …

Go to article

A Computational Framework For Learning From Complex Data: Formulations, Algorithms, And Applications, Wenlu Zhang Jul 2016

A Computational Framework For Learning From Complex Data: Formulations, Algorithms, And Applications, Wenlu Zhang

Computer Science Theses & Dissertations

Many real-world processes are dynamically changing over time. As a consequence, the observed complex data generated by these processes also evolve smoothly. For example, in computational biology, the expression data matrices are evolving, since gene expression controls are deployed sequentially during development in many biological processes. Investigations into the spatial and temporal gene expression dynamics are essential for understanding the regulatory biology governing development. In this dissertation, I mainly focus on two types of complex data: genome-wide spatial gene expression patterns in the model organism fruit fly and Allen Brain Atlas mouse brain data. I provide a framework to explore …

Go to article

Energy Consumption Prediction With Big Data: Balancing Prediction Accuracy And Computational Resources, Katarina Grolinger, Miriam Am Capretz, Luke Seewald Jun 2016

Energy Consumption Prediction With Big Data: Balancing Prediction Accuracy And Computational Resources, Katarina Grolinger, Miriam Am Capretz, Luke Seewald

Electrical and Computer Engineering Publications

In recent years, advances in sensor technologies and expansion of smart meters have resulted in massive growth of energy data sets. These Big Data have created new opportunities for energy prediction, but at the same time, they impose new challenges for traditional technologies. On the other hand, new approaches for handling and processing these Big Data have emerged, such as MapReduce, Spark, Storm, and Oxdata H2O. This paper explores how findings from machine learning with Big Data can benefit energy consumption prediction. An approach based on local learning with support vector regression (SVR) is presented. Although local learning itself is …

Go to article

Deepsense: A Gpu-Based Deep Convolutional Neural Network Framework On Commodity Mobile Devices, Huynh Nguyen Loc, Rajesh Krishna Balan, Youngki Lee Jun 2016

Deepsense: A Gpu-Based Deep Convolutional Neural Network Framework On Commodity Mobile Devices, Huynh Nguyen Loc, Rajesh Krishna Balan, Youngki Lee

Research Collection School Of Computing and Information Systems

Recently, a branch of machine learning algorithms called deep learning gained huge attention to boost up accuracy of a variety of sensing applications. However, execution of deep learning algorithm such as convolutional neural network on mobile processor is non-trivial due to intensive computational requirements. In this paper, we present our early design of DeepSense - a mobile GPU-based deep convolutional neural network (CNN) framework. For its design, we first explored the differences between server-class and mobile-class GPUs, and studied effectiveness of various optimization strategies such as branch divergence elimination and memory vectorization. Our results show that DeepSense is able to …

Go to article

Demo: Gpu-Based Image Recognition And Object Detection On Commodity Mobile Devices, Loc Nguyen Huynh, Rajesh Krishna Balan, Youngki Lee Jun 2016

Demo: Gpu-Based Image Recognition And Object Detection On Commodity Mobile Devices, Loc Nguyen Huynh, Rajesh Krishna Balan, Youngki Lee

Research Collection School Of Computing and Information Systems

In this demo, we show that it is feasible to execute CNN for vision sensing tasks directly on mobile devices by leveraging integrated GPU. We propose our design of DeepSense framework based on OpenCL to execute deep learning algorithms in energy-efficient and fast manner.

Go to article

Using Perceptually Grounded Semantic Models To Autonomously Convey Meaning Through Visual Art, Derrall L. Heath Jun 2016

Using Perceptually Grounded Semantic Models To Autonomously Convey Meaning Through Visual Art, Derrall L. Heath

Theses and Dissertations

Developing advanced semantic models is important in building computational systems that can not only understand language but also convey ideas and concepts to others. Semantic models can allow a creative image-producing-agent to autonomously produce artifacts that communicate an intended meaning. This notion of communicating meaning through art is often considered a necessary part of eliciting an aesthetic experience in the viewer and can thus enhance the (perceived) creativity of the agent. Computational creativity, a subfield of artificial intelligence, deals with designing computational systems and algorithms that either automatically create original and functional products, or that augment the ability of humans …

Go to article

Automatic Classification Of Perceived Gender From Face Images, Joseph Lemley, Sami Abdul-Wahid, Dipayan Banik May 2016

Automatic Classification Of Perceived Gender From Face Images, Joseph Lemley, Sami Abdul-Wahid, Dipayan Banik

Symposium Of University Research and Creative Expression (SOURCE)

Building software that can visually and accurately perceive gender from face images is an important step in making more intelligent machines. Several approaches to this problem have been suggested in the literature. We evaluate Histogram of Oriented Gradients, Dual Tree Complex Wavelet Transform (DTCWT) Principal Component Analysis (PCA) with Support Vector Machines (SVM) and compare them to Convolutional Neural Networks for this task. We train and test our classifiers with two benchmarks containing thousands of facial images. As expected, convolutional neural networks had the best performance while the performance of DTCWT varied most depending on the dataset used

Go to article

Sparse Feature Learning For Image Analysis In Segmentation, Classification, And Disease Diagnosis., Ehsan Hosseini-Asl May 2016

Sparse Feature Learning For Image Analysis In Segmentation, Classification, And Disease Diagnosis., Ehsan Hosseini-Asl

Electronic Theses and Dissertations

The success of machine learning algorithms generally depends on intermediate data representation, called features that disentangle the hidden factors of variation in data. Moreover, machine learning models are required to be generalized, in order to reduce the specificity or bias toward the training dataset. Unsupervised feature learning is useful in taking advantage of large amount of unlabeled data, which is available to capture these variations. However, learned features are required to capture variational patterns in data space. In this dissertation, unsupervised feature learning with sparsity is investigated for sparse and local feature extraction with application to lung segmentation, interpretable deep …

Go to article

Learning From Minimally Labeled Data With Accelerated Convolutional Neural Networks, Aysegul Dundar Apr 2016

Learning From Minimally Labeled Data With Accelerated Convolutional Neural Networks, Aysegul Dundar

Open Access Dissertations

The main objective of an Artificial Vision Algorithm is to design a mapping function that takes an image as an input and correctly classifies it into one of the user-determined categories. There are several important properties to be satisfied by the mapping function for visual understanding. First, the function should produce good representations of the visual world, which will be able to recognize images independently of pose, scale and illumination. Furthermore, the designed artificial vision system has to learn these representations by itself. Recent studies on Convolutional Neural Networks (ConvNets) produced promising advancements in visual understanding. These networks attain significant …

Go to article

Probabilistic And Deep Learning Algorithms For The Analysis Of Imagery Data, Saikat Basu Jan 2016

Probabilistic And Deep Learning Algorithms For The Analysis Of Imagery Data, Saikat Basu

LSU Doctoral Dissertations

Accurate object classification is a challenging problem for various low to high resolution imagery data. This applies to both natural as well as synthetic image datasets. However, each object recognition dataset poses its own distinct set of domain-specific problems. In order to address these issues, we need to devise intelligent learning algorithms which require a deep understanding and careful analysis of the feature space. In this thesis, we introduce three new learning frameworks for the analysis of both airborne images (NAIP dataset) and handwritten digit datasets without and with noise (MNIST and n-MNIST respectively). First, we propose a probabilistic framework …

Go to article

Big Data-Enabled Multiscale Serviceability Analysis For Aging Bridges, Yu Liang, Dalei Wu, Guirong Liu, Yaohang Li, Cuilan Gao, Zhongguo John Ma, Weidong Wu Jan 2016

Big Data-Enabled Multiscale Serviceability Analysis For Aging Bridges, Yu Liang, Dalei Wu, Guirong Liu, Yaohang Li, Cuilan Gao, Zhongguo John Ma, Weidong Wu

Computer Science Faculty Publications

This work is dedicated to constructing a multi-scale structural health monitoring system to monitor and evaluate the serviceability of bridges based on the Hadoop Ecosystem (MS-SHM-Hadoop). By taking the advantages of the fault-tolerant distributed file system called the Hadoop Distributed File System (HDFS) and high-performance parallel data processing engine called MapReduce programming paradigm, MS-SHM-Hadoop features include high scalability and robustness in data ingestion, fusion, processing, retrieval, and analytics. MS-SHM-Hadoop is a multi-scale reliability analysis framework, which ranges from nationwide bridge-surveys, global structural integrity analysis, and structural component reliability analysis. This Nationwide bridge survey uses deep-learning techniques to evaluate the bridge …

Go to article

Supercnn: A Superpixelwise Convolutional Neural Network For Salient Object Detection, Shengfeng He, Rynson W.H. Lau, Wenxi Liu, Zhe Huang, Qingxiong Yang Dec 2015

Supercnn: A Superpixelwise Convolutional Neural Network For Salient Object Detection, Shengfeng He, Rynson W.H. Lau, Wenxi Liu, Zhe Huang, Qingxiong Yang

Research Collection School Of Computing and Information Systems

Existing computational models for salient object detection primarily rely on hand-crafted features, which are only able to capture low-level contrast information. In this paper, we learn the hierarchical contrast features by formulating salient object detection as a binary labeling problem using deep learning techniques. A novel superpixelwise convolutional neural network approach, called SuperCNN, is proposed to learn the internal representations of saliency in an efficient manner. In contrast to the classical convolutional networks, SuperCNN has four main properties. First, the proposed method is able to learn the hierarchical contrast features, as it is fed by two meaningful superpixel sequences, which …

Go to article

A Robust Deep Model For Improved Classification Of Ad/Mci Patients, Feng Li, Loc Tran, Kim-Han Thung, Shuiwang Ji, Dinggang Shen, Jiang Li Jan 2015

A Robust Deep Model For Improved Classification Of Ad/Mci Patients, Feng Li, Loc Tran, Kim-Han Thung, Shuiwang Ji, Dinggang Shen, Jiang Li

Electrical & Computer Engineering Faculty Publications

Accurate classification of Alzheimer's disease (AD) and its prodromal stage, mild cognitive impairment (MCI), plays a critical role in possibly preventing progression of memory impairment and improving quality of life for AD patients. Among many research tasks, it is of a particular interest to identify noninvasive imaging biomarkers for AD diagnosis. In this paper, we present a robust deep learning system to identify different progression stages of AD patients based on MRI and PET scans. We utilized the dropout technique to improve classical deep learning by preventing its weight coadaptation, which is a typical cause of overfitting in deep learning. …

Go to article

Deep Learning For Content-Based Image Retrieval: A Comprehensive Study, Ji Wan, Dayong Wang, Steven C. H. Hoi, Pengcheng Wu, Jianke Zhu, Yongdong Zhang, Jintao Li Nov 2014

Deep Learning For Content-Based Image Retrieval: A Comprehensive Study, Ji Wan, Dayong Wang, Steven C. H. Hoi, Pengcheng Wu, Jianke Zhu, Yongdong Zhang, Jintao Li

Research Collection School Of Computing and Information Systems

Learning effective feature representations and similarity measures are crucial to the retrieval performance of a content-based image retrieval (CBIR) system. Despite extensive research efforts for decades, it remains one of the most challenging open problems that considerably hinders the successes of real-world CBIR systems. The key challenge has been attributed to the well-known "semantic gap" issue that exists between low-level image pixels captured by machines and high-level semantic concepts perceived by human. Among various techniques, machine learning has been actively investigated as a possible direction to bridge the semantic gap in the long term. Inspired by recent successes of deep …

Go to article

Online Multimodal Distance Metric Learning With Application To Image Retrieval, Pengcheng Wu, Steven C. H. Hoi, Hao Xia, Peilin Zhao, Dayong Wang, Chunyan Miao Oct 2013

Online Multimodal Distance Metric Learning With Application To Image Retrieval, Pengcheng Wu, Steven C. H. Hoi, Hao Xia, Peilin Zhao, Dayong Wang, Chunyan Miao

Research Collection School Of Computing and Information Systems

Recent years have witnessed extensive studies on distance metric learning (DML) for improving similarity search in multimedia information retrieval tasks. Despite their successes, most existing DML methods suffer from two critical limitations: (i) they typically attempt to learn a linear distance function on the input feature space, in which the assumption of linearity limits their capacity of measuring the similarity on complex patterns in real-world applications; (ii) they are often designed for learning distance metrics on uni-modal data, which may not effectively handle the similarity measures for multimedia objects with multimodal representations. To address these limitations, in this paper, we …

Go to article

Online Multi-Stage Deep Architectures For Feature Extraction And Object Recognition, Derek Christopher Rose Aug 2013

Online Multi-Stage Deep Architectures For Feature Extraction And Object Recognition, Derek Christopher Rose

Doctoral Dissertations

Multi-stage visual architectures have recently found success in achieving high classification accuracies over image datasets with large variations in pose, lighting, and scale. Inspired by techniques currently at the forefront of deep learning, such architectures are typically composed of one or more layers of preprocessing, feature encoding, and pooling to extract features from raw images. Training these components traditionally relies on large sets of patches that are extracted from a potentially large image dataset. In this context, high-dimensional feature space representations are often helpful for obtaining the best classification performances and providing a higher degree of invariance to object transformations. …

Go to article

First Prev