This paper studies deep network architectures to address the problem of video classification. A multi-stream framework is proposed to fully utilize the rich multimodal information in videos. Specifically, we first train three Convolutional Neural Networks to model spatial, short-term motion and audio clues respectively. Long Short Term Memory networks are then adopted to explore long-term temporal dynamics. With the outputs of the individual streams, we propose a simple and effective fusion method to generate the final predictions, where the optimal fusion weights are learned adaptively for each class, and the learning process is regularized by automatically estimated class relationships. Our contributions are two-fold. First, the proposed multi-stream framework is able to exploit multimodal features that are more comprehensive than those previously attempted. Second, we demonstrate that the adaptive fusion method using the class relationship as a regularizer outperforms traditional alternatives that estimate the weights in a "free" fashion. Our framework produces significantly better results than the state of the arts on two popular benchmarks, 92.2\% on UCF-101 (without using audio) and 84.9\% on Columbia Consumer Videos.
Automatic diagnosis of coronary heart disease helps the doctor to support in decision making a diagnosis. Coronary heart disease have some types or levels. Referring to the UCI Repository dataset, it divided into 4 types or levels that are labeled numbers 1-4 (low, medium, high and serious). The diagnosis models can be analyzed with multiclass classification approach. One of multiclass classification approach used, one of which is a support vector machine (SVM). The SVM use due to strong performance of SVM in binary classification. This research study multiclass performance classification support vector machine to diagnose the type or level of coronary heart disease. Coronary heart disease patient data taken from the UCI Repository. Stages in this study is preprocessing, which consist of, to normalizing the data, divide the data into data training and testing. The next stage of multiclass classification and performance analysis. This study uses multiclass SVM algorithm, namely: Binary Tree Support Vector Machine (BTSVM), One-Against-One (OAO), One-Against-All (OAA), Decision Direct Acyclic Graph (DDAG) and Exhaustive Output Error Correction Code (ECOC). Performance parameter used is recall, precision, F-measure and Overall accuracy.
This paper aims to accelerate the test-time computation of convolutional neural networks (CNNs), especially very deep CNNs that have substantially impacted the computer vision community. Unlike previous methods that are designed for approximating linear filters or linear responses, our method takes the nonlinear units into account. We develop an effective solution to the resulting nonlinear optimization problem without the need of stochastic gradient descent (SGD). More importantly, while previous methods mainly focus on optimizing one or two layers, our nonlinear method enables an asymmetric reconstruction that reduces the rapidly accumulated error when multiple (e.g., >=10) layers are approximated. For the widely used very deep VGG-16 model, our method achieves a whole-model speedup of 4x with merely a 0.3% increase of top-5 error in ImageNet classification. Our 4x accelerated VGG-16 model also shows a graceful accuracy degradation for object detection when plugged into the Fast R-CNN detector.
Non-sentential utterances (NSUs) are utterances that lack a complete sentential form but whose meaning can be inferred from the dialogue context, such as "OK", "where?", "probably at his apartment". The interpretation of non-sentential utterances is an important problem in computational linguistics since they constitute a frequent phenomena in dialogue and they are intrinsically context-dependent. The interpretation of NSUs is the task of retrieving their full semantic content from their form and the dialogue context. The first half of this thesis is devoted to the NSU classification task. Our work builds upon Fern\'andez et al. (2007) which present a series of machine-learning experiments on the classification of NSUs. We extended their approach with a combination of new features and semi-supervised learning techniques. The empirical results presented in this thesis show a modest but significant improvement over the state-of-the-art classification performance. The consecutive, yet independent, problem is how to infer an appropriate semantic representation of such NSUs on the basis of the dialogue context. Fern\'andez (2006) formalizes this task in terms of "resolution rules" built on top of the Type Theory with Records (TTR). Our work is focused on the reimplementation of the resolution rules from Fern\'andez (2006) with a probabilistic account of the dialogue state. The probabilistic rules formalism Lison (2014) is particularly suited for this task because, similarly to the framework developed by Ginzburg (2012) and Fern\'andez (2006), it involves the specification of update rules on the variables of the dialogue state to capture the dynamics of the conversation. However, the probabilistic rules can also encode probabilistic knowledge, thereby providing a principled account of ambiguities in the NSU resolution process.
Multivariate classification methods using explanatory and predictive models are necessary for characterizing subgroups of patients according to their risk profiles. Popular methods include logistic regression and classification trees with performances that vary according to the nature and the characteristics of the dataset. In the context of imported malaria, we aimed at classifying severity criteria based on a heterogeneous patient population. We investigated these approaches by implementing two different strategies: L1 logistic regression (L1LR) that models a single global solution and classification trees that model multiple local solutions corresponding to discriminant subregions of the feature space. For each strategy, we built a standard model, and a sparser version of it. As an alternative to pruning, we explore a promising approach that first constrains the tree model with an L1LR-based feature selection, an approach we called L1LR-Tree. The objective is to decrease its vulnerability to small data variations by removing variables corresponding to unstable local phenomena. Our study is twofold: i) from a methodological perspective comparing the performances and the stability of the three previous methods, i.e L1LR, classification trees and L1LR-Tree, for the classification of severe forms of imported malaria, and ii) from an applied perspective improving the actual classification of severe forms of imported malaria by identifying more personalized profiles predictive of several clinical criteria based on variables dismissed for the clinical definition of the disease. The main methodological results show that the combined method L1LR-Tree builds sparse and stable models that significantly predicts the different severity criteria and outperforms all the other methods in terms of accuracy.
Modern machine learning-based recognition approaches require large-scale datasets with large number of labelled training images. However, such datasets are inherently difficult and costly to collect and annotate. Hence there is a great and growing interest in automatic dataset collection methods that can leverage the web. % which are collected % in a cheap, efficient and yet unreliable way. Collecting datasets in this way, however, requires robust and efficient ways for detecting and excluding outliers that are common and prevalent. % Outliers are thus a % prominent treat of using these dataset. So far, there have been a limited effort in machine learning community to directly detect outliers for robust classification. Inspired by the recent work on Pre-conditioned LASSO, this paper formulates the outlier detection task using Pre-conditioned LASSO and employs \red{unsupervised} transductive diffusion component analysis to both integrate the topological structure of the data manifold, from labeled and unlabeled instances, and reduce the feature dimensionality. Synthetic experiments as well as results on two real-world classification tasks show that our framework can robustly detect the outliers and improve classification.
Machine learning relies on the assumption that unseen test instances of a classification problem follow the same distribution as observed training data. However, this principle can break down when machine learning is used to make important decisions about the welfare (employment, education, health) of strategic individuals. Knowing information about the classifier, such individuals may manipulate their attributes in order to obtain a better classification outcome. As a result of this behavior---often referred to as gaming---the performance of the classifier may deteriorate sharply. Indeed, gaming is a well-known obstacle for using machine learning methods in practice; in financial policy-making, the problem is widely known as Goodhart's law. In this paper, we formalize the problem, and pursue algorithms for learning classifiers that are robust to gaming. We model classification as a sequential game between a player named "Jury" and a player named "Contestant." Jury designs a classifier, and Contestant receives an input to the classifier, which he may change at some cost. Jury's goal is to achieve high classification accuracy with respect to Contestant's original input and some underlying target classification function. Contestant's goal is to achieve a favorable classification outcome while taking into account the cost of achieving it. For a natural class of cost functions, we obtain computationally efficient learning algorithms which are near-optimal. Surprisingly, our algorithms are efficient even on concept classes that are computationally hard to learn. For general cost functions, designing an approximately optimal strategy-proof classifier, for inverse-polynomial approximation, is NP-hard.
We show that multiple machine learning algorithms can match human performance in classifying transient imaging data from the Sloan Digital Sky Survey (SDSS) supernova survey into real objects and artefacts. This is a first step in any transient science pipeline and is currently still done by humans, but future surveys such as the Large Synoptic Survey Telescope (LSST) will necessitate fully machine-enabled solutions. Using features trained from eigenimage analysis (principal component analysis, PCA) of single-epoch g, r and i-difference images, we can reach a completeness (recall) of 96 per cent, while only incorrectly classifying at most 18 per cent of artefacts as real objects, corresponding to a precision (purity) of 84 per cent. In general, random forests performed best, followed by the k-nearest neighbour and the SkyNet artificial neural net algorithms, compared to other methods such as na\"ive Bayes and kernel support vector machine. Our results show that PCA-based machine learning can match human success levels and can naturally be extended by including multiple epochs of data, transient colours and host galaxy information which should allow for significant further improvements, especially at low signal-to-noise.
In this paper, we attempt to classify tweets into root categories of the Amazon browse node hierarchy using a set of tweets with browse node ID labels, a much larger set of tweets without labels, and a set of Amazon reviews. Examining twitter data presents unique challenges in that the samples are short (under 140 characters) and often contain misspellings or abbreviations that are trivial for a human to decipher but difficult for a computer to parse. A variety of query and document expansion techniques are implemented in an effort to improve information retrieval to modest success.
This paper introduces the use of single layer and deep convolutional networks for remote sensing data analysis. Direct application to multi- and hyper-spectral imagery of supervised (shallow or deep) convolutional networks is very challenging given the high input data dimensionality and the relatively small amount of available labeled data. Therefore, we propose the use of greedy layer-wise unsupervised pre-training coupled with a highly efficient algorithm for unsupervised learning of sparse features. The algorithm is rooted on sparse representations and enforces both population and lifetime sparsity of the extracted features, simultaneously. We successfully illustrate the expressive power of the extracted representations in several scenarios: classification of aerial scenes, as well as land-use classification in very high resolution (VHR), or land-cover classification from multi- and hyper-spectral images. The proposed algorithm clearly outperforms standard Principal Component Analysis (PCA) and its kernel counterpart (kPCA), as well as current state-of-the-art algorithms of aerial classification, while being extremely computationally efficient at learning representations of data. Results show that single layer convolutional networks can extract powerful discriminative features only when the receptive field accounts for neighboring pixels, and are preferred when the classification requires high resolution and detailed results. However, deep architectures significantly outperform single layers variants, capturing increasing levels of abstraction and complexity throughout the feature hierarchy.
This paper attempts multi-label classification by extending the idea of independent binary classification models for each output label, and exploring how the inherent correlation between output labels can be used to improve predictions. Logistic Regression, Naive Bayes, Random Forest, and SVM models were constructed, with SVM giving the best results: an improvement of 12.9\% over binary models was achieved for hold out cross validation by augmenting with pairwise correlation probabilities of the labels.
This paper proposes algorithms for learning two-level Boolean rules in Conjunctive Normal Form (CNF, i.e. AND-of-ORs) or Disjunctive Normal Form (DNF, i.e. OR-of-ANDs) as a type of human-interpretable classification model, aiming for a favorable trade-off between the classification accuracy and the simplicity of the rule. Two formulations are proposed. The first is an integer program whose objective function is a combination of the total number of errors and the total number of features used in the rule. We generalize a previously proposed linear programming (LP) relaxation from one-level to two-level rules. The second formulation replaces the 0-1 classification error with the Hamming distance from the current two-level rule to the closest rule that correctly classifies a sample. Based on this second formulation, block coordinate descent and alternating minimization algorithms are developed. Experiments show that the two-level rules can yield noticeably better performance than one-level rules due to their dramatically larger modeling capacity, and the two algorithms based on the Hamming distance formulation are generally superior to the other two-level rule learning methods in our comparison. A proposed approach to binarize any fractional values in the optimal solutions of LP relaxations is also shown to be effective.
Power quality (PQ) analysis describes the non-pure electric signals that are usually present in electric power systems. The automatic recognition of PQ disturbances can be seen as a pattern recognition problem, in which different types of waveform distortion are differentiated based on their features. Similar to other quasi-stationary signals, PQ disturbances can be decomposed into time-frequency dependent components by using time-frequency or time-scale transforms, also known as dictionaries. These dictionaries are used in the feature extraction step in pattern recognition systems. Short-time Fourier, Wavelets and Stockwell transforms are some of the most common dictionaries used in the PQ community, aiming to achieve a better signal representation. To the best of our knowledge, previous works about PQ disturbance classification have been restricted to the use of one among several available dictionaries. Taking advantage of the theory behind sparse linear models (SLM), we introduce a sparse method for PQ representation, starting from overcomplete dictionaries. In particular, we apply Group Lasso. We employ different types of time-frequency (or time-scale) dictionaries to characterize the PQ disturbances, and evaluate their performance under different pattern recognition algorithms. We show that the SLM reduce the PQ classification complexity promoting sparse basis selection, and improving the classification accuracy.
Fisher Vector classifiers and Deep Neural Networks (DNNs) are popular and successful algorithms for solving image classification problems. However, both are generally considered `black box' predictors as the non-linear transformations involved have so far prevented transparent and interpretable reasoning. Recently, a principled technique, Layer-wise Relevance Propagation (LRP), has been developed in order to better comprehend the inherent structured reasoning of complex nonlinear classification models such as Bag of Feature models or DNNs. In this paper we (1) extend the LRP framework also for Fisher Vector classifiers and then use it as analysis tool to (2) quantify the importance of context for classification, (3) qualitatively compare DNNs against FV classifiers in terms of important image regions and (4) detect potential flaws and biases in data. All experiments are performed on the PASCAL VOC 2007 data set.
We present a novel deep convolutional neural network (DCNN) system for fine-grained image classification, called a mixture of DCNNs (MixDCNN). The fine-grained image classification problem is characterised by large intra-class variations and small inter-class variations. To overcome these problems our proposed MixDCNN system partitions images into K subsets of similar images and learns an expert DCNN for each subset. The output from each of the K DCNNs is combined to form a single classification decision. In contrast to previous techniques, we provide a formulation to perform joint end-to-end training of the K DCNNs simultaneously. Extensive experiments, on three datasets using two network structures (AlexNet and GoogLeNet), show that the proposed MixDCNN system consistently outperforms other methods. It provides a relative improvement of 12.7% and achieves state-of-the-art results on two datasets.
This paper considers Aspect-based Opinion Summarization (AOS) of reviews on particular products. To enable real applications, an AOS system needs to address two core subtasks, aspect extraction and sentiment classification. Most existing approaches to aspect extraction, which use linguistic analysis or topic modeling, are general across different products but not precise enough or suitable for particular products. Instead we take a less general but more precise scheme, directly mapping each review sentence into pre-defined aspects. To tackle aspect mapping and sentiment classification, we propose two Convolutional Neural Network (CNN) based methods, cascaded CNN and multitask CNN. Cascaded CNN contains two levels of convolutional networks. Multiple CNNs at level 1 deal with aspect mapping task, and a single CNN at level 2 deals with sentiment classification. Multitask CNN also contains multiple aspect CNNs and a sentiment CNN, but different networks share the same word embeddings. Experimental results indicate that both cascaded and multitask CNNs outperform SVM-based methods by large margins. Multitask CNN generally performs better than cascaded CNN.
Autonomous repair of deep-sea coral reefs is a recent proposed idea to support the oceans ecosystem in which is vital for commercial fishing, tourism and other species. This idea can be operated through using many small autonomous underwater vehicles (AUVs) and swarm intelligence techniques to locate and replace chunks of coral which have been broken off, thus enabling re-growth and maintaining the habitat. The aim of this project is developing machine vision algorithms to enable an underwater robot to locate a coral reef and a chunk of coral on the seabed and prompt the robot to pick it up. Although there is no literature on this particular problem, related work on fish counting may give some insight into the problem. The technical challenges are principally due to the potential lack of clarity of the water and platform stabilization as well as spurious artifacts (rocks, fish, and crabs). We present an efficient sparse classification for coral species using supervised deep learning method called Convolutional Neural Networks (CNNs). We compute Weber Local Descriptor (WLD), Phase Congruency (PC), and Zero Component Analysis (ZCA) Whitening to extract shape and texture feature descriptors, which are employed to be supplementary channels (feature-based maps) besides basic spatial color channels (spatial-based maps) of coral input image, we also experiment state-of-art preprocessing underwater algorithms for image enhancement and color normalization and color conversion adjustment. Our proposed coral classification method is developed under MATLAB platform, and evaluated by two different coral datasets (University of California San Diego's Moorea Labeled Corals, and Heriot-Watt University's Atlantic Deep Sea).
Many classification approaches first represent a test sample using the training samples of all the classes. This collaborative representation is then used to label the test sample. It was a common belief that sparseness of the representation is the key to success for this classification scheme. However, more recently, it has been claimed that it is the collaboration and not the sparseness that makes the scheme effective. This claim is attractive as it allows to relinquish the computationally expensive sparsity constraint over the representation. In this paper, we first extend the analysis supporting this claim and then show that sparseness explicitly contributes to improved classification, hence it should not be completely ignored for computational gains. Inspired by this result, we augment a dense collaborative representation with a sparse representation and propose an efficient classification method that capitalizes on the resulting representation. The augmented representation and the classification method work together meticulously to achieve higher accuracy and lower computational time compared to state-of-the-art collaborative representation based classification approaches. Experiments on benchmark face, object and action databases show the efficacy of our approach.
Support Vector Machines (SVMs) were primarily designed for 2-class classification. But they have been extended for N-class classification also based on the requirement of multiclasses in the practical applications. Although N-class classification using SVM has considerable research attention, getting minimum number of classifiers at the time of training and testing is still a continuing research. We propose a new algorithm CBTS-SVM (Centroid based Binary Tree Structured SVM) which addresses this issue. In this we build a binary tree of SVM models based on the similarity of the class labels by finding their distance from the corresponding centroids at the root level. The experimental results demonstrates the comparable accuracy for CBTS with OVO with reasonable gamma and cost values. On the other hand when CBTS is compared with OVA, it gives the better accuracy with reduced training time and testing time. Furthermore CBTS is also scalable as it is able to handle the large data sets.
A method for large scale Gaussian process classification has been recently proposed based on expectation propagation (EP). Such a method allows Gaussian process classifiers to be trained on very large datasets that were out of the reach of previous deployments of EP and has been shown to be competitive with related techniques based on stochastic variational inference. Nevertheless, the memory resources required scale linearly with the dataset size, unlike in variational methods. This is a severe limitation when the number of instances is very large. Here we show that this problem is avoided when stochastic EP is used to train the model.