Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

/pdf/convex-analysisnoer-san-nojin-zhan-nituite-5dl2rbmoyr.pdf

Convex Analysisの二,三の進展について

We propose a natural scene statistic-based distortion-generic blind/no-reference (NR) image quality assessment (IQA) model that operates in the spatial domain. The new model, dubbed blind/referenceless image spatial quality evaluator (BRISQUE) does not compute distortion-specific features, such as ringing, blur, or blocking, but instead uses scene statistics of locally normalized luminance coefficients to quantify possible losses of “naturalness” in the image due to the presence of distortions, thereby leading to a holistic measure of quality. The underlying features used derive from the empirical distribution of locally normalized luminances and products of locally normalized luminances under a spatial natural scene statistic model. No transformation to another coordinate frame (DCT, wavelet, etc.) is required, distinguishing it from prior NR IQA approaches. Despite its simplicity, we are able to show that BRISQUE is statistically better than the full-reference peak signal-to-noise ratio and the structural similarity index, and is highly competitive with respect to all present-day distortion-generic NR IQA algorithms. BRISQUE has very low computational complexity, making it well suited for real time applications. BRISQUE features may be used for distortion-identification as well. To illustrate a new practical application of BRISQUE, we describe how a nonblind image denoising algorithm can be augmented with BRISQUE in order to perform blind image denoising. Results show that BRISQUE augmentation leads to performance improvements over state-of-the-art methods. A software release of BRISQUE is available online: http://live.ece.utexas.edu/research/quality/BRISQUE_release.zip for public use and evaluation.

/pdf/no-reference-image-quality-assessment-in-the-spatial-domain-2mnlvf25ig.pdf

No-Reference Image Quality Assessment in the Spatial Domain

Due to object detection’s close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable architectures. Their performance easily stagnates by constructing complex ensembles that combine multiple low-level image features with high-level context from object detectors and scene classifiers. With the rapid development in deep learning, more powerful tools, which are able to learn semantic, high-level, deeper features, are introduced to address the problems existing in traditional architectures. These models behave differently in network architecture, training strategy, and optimization function. In this paper, we provide a review of deep learning-based object detection frameworks. Our review begins with a brief introduction on the history of deep learning and its representative tool, namely, the convolutional neural network. Then, we focus on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further. As distinct specific detection tasks exhibit different characteristics, we also briefly survey several specific tasks, including salient object detection, face detection, and pedestrian detection. Experimental analyses are also provided to compare various methods and draw some meaningful conclusions. Finally, several promising directions and tasks are provided to serve as guidelines for future work in both object detection and relevant neural network-based learning systems.

Object Detection With Deep Learning: A Review

Big Data Analytics and Deep Learning are two high-focus of data science. Big Data has become important as many organizations both public and private have been collecting massive amounts of domain-specific information, which can contain useful information about problems such as national intelligence, cyber security, fraud detection, marketing, and medical informatics. Companies such as Google and Microsoft are analyzing large volumes of data for business analysis and decisions, impacting existing and future technology. Deep Learning algorithms extract high-level, complex abstractions as data representations through a hierarchical learning process. Complex abstractions are learnt at a given level based on relatively simpler abstractions formulated in the preceding level in the hierarchy. A key benefit of Deep Learning is the analysis and learning of massive amounts of unsupervised data, making it a valuable tool for Big Data Analytics where raw data is largely unlabeled and un-categorized. In the present study, we explore how Deep Learning can be utilized for addressing some important problems in Big Data Analytics, including extracting complex patterns from massive volumes of data, semantic indexing, data tagging, fast information retrieval, and simplifying discriminative tasks. We also investigate some aspects of Deep Learning research that need further exploration to incorporate specific challenges introduced by Big Data Analytics, including streaming data, high-dimensional data, scalability of models, and distributed computing. We conclude by presenting insights into relevant future works by posing some questions, including defining data sampling criteria, domain adaptation modeling, defining criteria for obtaining useful data abstractions, improving semantic indexing, semi-supervised learning, and active learning.

/pdf/deep-learning-applications-and-challenges-in-big-data-oblfhz8zye.pdf

Deep learning applications and challenges in big data analytics

Support Vector Machine is one of the classical machine learning techniques that can still help solve big data classification problems. Especially, it can help the multidomain applications in a big data environment. However, the support vector machine is mathematically complex and computationally expensive. The main objective of this chapter is to simplify this approach using process diagrams and data flow diagrams to help readers understand theory and implement it successfully. To achieve this objective, the chapter is divided into three parts: (1) modeling of a linear support vector machine; (2) modeling of a nonlinear support vector machine; and (3) Lagrangian support vector machine algorithm and its implementations. The Lagrangian support vector machine with simple examples is also implemented using the R programming platform on Hadoop and non-Hadoop systems.

Support Vector Machine

Machine Learning Models and Algorithms for Big Data Classification

This paper focuses on the specific problem of Big Data classification of network intrusion traffic. It discusses the system challenges presented by the Big Data problems associated with network intrusion prediction. The prediction of a possible intrusion attack in a network requires continuous collection of traffic data and learning of their characteristics on the fly. The continuous collection of traffic data by the network leads to Big Data problems that are caused by the volume, variety and velocity properties of Big Data. The learning of the network characteristics require machine learning techniques that capture global knowledge of the traffic patterns. The Big Data properties will lead to significant system challenges to implement machine learning frameworks. This paper discusses the problems and challenges in handling Big Data classification using geometric representation-learning techniques and the modern Big Data networking technologies. In particular this paper discusses the issues related to combining supervised learning techniques, representation-learning techniques, machine lifelong learning techniques and Big Data technologies (e.g. Hadoop, Hive and Cloud) for solving network traffic classification problems.

/pdf/big-data-classification-problems-and-challenges-in-network-1vc3dx98fw.pdf

Big data classification: problems and challenges in network intrusion prediction with machine learning

The main objective of this chapter is to introduce you to hierarchical supervised learning models. One of the main hierarchical models is the decision tree. It has two categories: classification tree and regression tree. The theory and applications of these decision trees are explained in this chapter. These techniques require tree split algorithms to build the decision trees and require quantitative measures to build an efficient tree via training. Hence, the chapter dedicates some discussion to the measures like entropy, cross-entropy, Gini impurity, and information gain. It also discusses the training algorithms suitable for classification tree and regression tree models. Simple examples and visual aids explain the difficult concepts so that readers can easily grasp the theory and applications of decision tree.

Decision Tree Learning

Security of wireless sensor networks (WSN) is an important research area in computer and communications sciences. Anomaly detection is a key challenge in ensuring the security of WSN. Several anomaly detection algorithms have been proposed and validated recently using labeled datasets that are not publicly available. Our group proposed an ellipsoid-based anomaly detection algorithm but demonstrated its performance using synthetic datasets and real Intel Berkeley Research Laboratory and Grand St. Bernard datasets which are not labeled with anomalies. This approach requires manual assignment of the anomalies' positions based on visual estimates for performance evaluation. In this paper, we have implemented a single-hop and multi-hop sensor-data collection network. In both scenarios we generated real labeled data for anomaly detection and identified different types of anomalies. These labeled sensor data and types of anomalies are useful for research, such as machine learning, and this information will be disseminated to the research community.

Shan Suthaharan

Papers

Support Vector Machine

Machine Learning Models and Algorithms for Big Data Classification

Big data classification: problems and challenges in network intrusion prediction with machine learning

Decision Tree Learning

Labelled data collection for anomaly detection in wireless sensor networks