We present a method to classify objects in video streams using a brain-inspired Hierarchical Temporal Memory (HTM) algorithm. Object classification is a challenging task where humans still significantly outperform machine learning algorithms due to their unique capabilities. We have implemented a system which achieves very promising performance in terms of recognition accuracy. Unfortunately, conducting more advanced experiments is very computationally demanding; some of the trials run on a standard CPU may take as long as several days for 960x540 video streams frames. Therefore we have decided to accelerate selected parts of the system using OpenCL. In particular, we seek to determine to what extent porting selected and computationally demanding parts of a core may speed up calculations. The classification accuracy of the system was examined through a series of experiments and the performance was given in terms of F1 score as a function of the number of columns, synapses, $min\_overlap$ and $winners\_set\_size$. The system achieves the highest F1 score of 0.95 and 0.91 for $min\_overlap=4$ and 256 synapses, respectively. We have also conduced a series of experiments with different hardware setups and measured CPU/GPU acceleration. The best kernel speed-up of 632x and 207x was reached for 256 synapses and 1024 columns. However, overall acceleration including transfer time was significantly lower and amounted to 6.5x and 3.2x for the same setup.
Multiview assisted learning has gained significant attention in recent years in supervised learning genre. Availability of high performance computing devices enables learning algorithms to search simultaneously over multiple views or feature spaces to obtain an optimum classification performance. The paper is a pioneering attempt of formulating a mathematical foundation for realizing a multiview aided collaborative boosting architecture for multiclass classification. Most of the present algorithms apply multiview learning heuristically without exploring the fundamental mathematical changes imposed on traditional boosting. Also, most of the algorithms are restricted to two class or view setting. Our proposed mathematical framework enables collaborative boosting across any finite dimensional view spaces for multiclass learning. The boosting framework is based on forward stagewise additive model which minimizes a novel exponential loss function. We show that the exponential loss function essentially captures difficulty of a training sample space instead of the traditional `1/0' loss. The new algorithm restricts a weak view from over learning and thereby preventing overfitting. The model is inspired by our earlier attempt on collaborative boosting which was devoid of mathematical justification. The proposed algorithm is shown to converge much nearer to global minimum in the exponential loss space and thus supersedes our previous algorithm. The paper also presents analytical and numerical analysis of convergence and margin bounds for multiview boosting algorithms and we show that our proposed ensemble learning manifests lower error bound and higher margin compared to our previous model. Also, the proposed model is compared with traditional boosting and recent multiview boosting algorithms.
Deep learning architectures are showing great promise in various computer vision domains including image classification, object detection, event detection and action recognition. In this study, we investigate various aspects of convolutional neural networks (CNNs) from the big data perspective. We analyze recent studies and different network architectures both in terms of running time and accuracy. We present extensive empirical information along with best practices for big data practitioners. Using these best practices we propose efficient fusion mechanisms both for single and multiple network models. We present state-of-the art results on benchmark datasets while keeping computational costs at a lower level. Another contribution of our paper is that these state-of-the-art results can be reached without using extensive data augmentation techniques.
Deep convolutional neural network (DCNN) has achieved remarkable performance on object detection and speech recognition in recent years. However, the excellent performance of a DCNN incurs high computational complexity and large memory requirement. In this paper, an equal distance nonuniform quantization (ENQ) scheme and a K-means clustering nonuniform quantization (KNQ) scheme are proposed to reduce the required memory storage when low complexity hardware or software implementations are considered. For the VGG-16 and the AlexNet, the proposed nonuniform quantization schemes reduce the number of required memory storage by approximately 50\% while achieving almost the same or even better classification accuracy compared to the state-of-the-art quantization method. Compared to the ENQ scheme, the proposed KNQ scheme provides a better tradeoff when higher accuracy is required.
We address the vehicle detection and classification problems using Deep Neural Networks (DNNs) approaches. Here we answer to questions that are specific to our application including how to utilize DNN for vehicle detection, what features are useful for vehicle classification, and how to extend a model trained on a limited size dataset, to the cases of extreme lighting condition. Answering these questions we propose our approach that outperforms state-of-the-art methods, and achieves promising results on image with extreme lighting conditions.
Sparse coding with dictionary learning (DL) has shown excellent classification performance. Despite the considerable number of existing works, how to obtain features on top of which dictionaries can be better learned remains an open and interesting question. Many current prevailing DL methods directly adopt well-performing crafted features. While such strategy may empirically work well, it ignores certain intrinsic relationship between dictionaries and features. We propose a framework where features and dictionaries are jointly learned and optimized. The framework, named joint non-negative projection and dictionary learning (JNPDL), enables interaction between the input features and the dictionaries. The non-negative projection leads to discriminative parts-based object features while DL seeks a more suitable representation. Discriminative graph constraints are further imposed to simultaneously maximize intra-class compactness and inter-class separability. Experiments on both image and image set classification show the excellent performance of JNPDL by outperforming several state-of-the-art approaches.
In many real-world classification problems, the labels of training examples are randomly corrupted. Most previous theoretical work on classification with label noise assumes that the two classes are separable, that the label noise is independent of the true class label, or that the noise proportions for each class are known. In this work, we give conditions that are necessary and sufficient for the true class-conditional distributions to be identifiable. These conditions are weaker than those analyzed previously, and allow for the classes to be nonseparable and the noise levels to be asymmetric and unknown. The conditions essentially state that a majority of the observed labels are correct and that the true class-conditional distributions are "mutually irreducible," a concept we introduce that limits the similarity of the two distributions. For any label noise problem, there is a unique pair of true class-conditional distributions satisfying the proposed conditions, and we argue that this pair corresponds in a certain sense to maximal denoising of the observed distributions. Our results are facilitated by a connection to "mixture proportion estimation," which is the problem of estimating the maximal proportion of one distribution that is present in another. We establish a novel rate of convergence result for mixture proportion estimation, and apply this to obtain consistency of a discrimination rule based on surrogate loss minimization. Experimental results on benchmark data and a nuclear particle classification problem demonstrate the efficacy of our approach.
The role of social media, in particular microblogging platforms such as Twitter, as a conduit for actionable and tactical information during disasters is increasingly acknowledged. However, time-critical analysis of big crisis data on social media streams brings challenges to machine learning techniques, especially the ones that use supervised learning. The Scarcity of labeled data, particularly in the early hours of a crisis, delays the machine learning process. The current state-of-the-art classification methods require a significant amount of labeled data specific to a particular event for training plus a lot of feature engineering to achieve best results. In this work, we introduce neural network based classification methods for binary and multi-class tweet classification task. We show that neural network based models do not require any feature engineering and perform better than state-of-the-art methods. In the early hours of a disaster when no labeled data is available, our proposed method makes the best use of the out-of-event data and achieves good results.
We propose a procedure for supervised classification that is based on potential functions. The potential of a class is defined as a kernel density estimate multiplied by the class's prior probability. The method transforms the data to a potential-potential (pot-pot) plot, where each data point is mapped to a vector of potentials. Separation of the classes, as well as classification of new data points, is performed on this plot. For this, either the $\alpha$-procedure ($\alpha$-P) or $k$-nearest neighbors ($k$-NN) are employed. For data that are generated from continuous distributions, these classifiers prove to be strongly Bayes-consistent. The potentials depend on the kernel and its bandwidth used in the density estimate. We investigate several variants of bandwidth selection, including joint and separate pre-scaling and a bandwidth regression approach. The new method is applied to benchmark data from the literature, including simulated data sets as well as 50 sets of real data. It compares favorably to known classification methods such as LDA, QDA, max kernel density estimates, $k$-NN, and $DD$-plot classification using depth functions.
In this paper, we present a deep neural network (DNN)-based acoustic scene classification framework. Two hierarchical learning methods are proposed to improve the DNN baseline performance by incorporating the hierarchical taxonomy information of environmental sounds. Firstly, the parameters of the DNN are initialized by the proposed hierarchical pre-training. Multi-level objective function is then adopted to add more constraint on the cross-entropy based loss function. A series of experiments were conducted on the Task1 of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2016 challenge. The final DNN-based system achieved a 22.9% relative improvement on average scene classification error as compared with the Gaussian Mixture Model (GMM)-based benchmark system across four standard folds.
This paper explores a simple and efficient baseline for text classification. Our experiments show that our fast text classifier fastText is often on par with deep learning classifiers in terms of accuracy, and many orders of magnitude faster for training and evaluation. We can train fastText on more than one billion words in less than ten minutes using a standard multicore~CPU, and classify half a million sentences among~312K classes in less than a minute.
Acoustic event detection for content analysis in most cases relies on lots of labeled data. However, manually annotating data is a time-consuming task, which thus makes few annotated resources available so far. Unlike audio event detection, automatic audio tagging, a multi-label acoustic event classification task, only relies on weakly labeled data. This is highly desirable to some practical applications using audio analysis. In this paper we propose to use a fully deep neural network (DNN) framework to handle the multi-label classification task in a regression way. Considering that only chunk-level rather than frame-level labels are available, the whole or almost whole frames of the chunk were fed into the DNN to perform a multi-label regression for the expected tags. The fully DNN, which is regarded as an encoding function, can well map the audio features sequence to a multi-tag vector. A deep pyramid structure was also designed to extract more robust high-level features related to the target tags. Further improved methods were adopted, such as the Dropout and background noise aware training, to enhance its generalization capability for new audio recordings in mismatched environments. Compared with the conventional Gaussian Mixture Model (GMM) and support vector machine (SVM) methods, the proposed fully DNN-based method could well utilize the long-term temporal information with the whole chunk as the input. The results show that our approach obtained a 15% relative improvement compared with the official GMM-based method of DCASE 2016 challenge.
Classification is the task of predicting the class labels of objects based on the observation of their features. In contrast, quantification has been defined as the task of determining the prevalences of the different sorts of class labels in a target dataset. The simplest approach to quantification is Classify & Count where a classifier is optimised for classification on a training set and applied to the target dataset for the prediction of class labels. In the case of binary quantification, the number of predicted positive labels is then used as an estimate of the prevalence of the positive class in the target dataset. Since the performance of Classify & Count for quantification is known to be inferior its results typically are subject to adjustments. However, some researchers recently have suggested that Classify & Count might actually work without adjustments if it is based on a classifer that was specifically trained for quantification. We discuss the theoretical foundation for this claim and explore its potential and limitations with a numerical example based on the binormal model with equal variances. In order to identify an optimal quantifier in the binormal setting, we introduce the concept of local Bayes optimality. As a side remark, we present a complete proof of a theorem by Ye et al. (2012).
Disease prediction or classification using health datasets involve using well-known predictors associated with the disease as features for the models. This study considers multiple data components of an individual's health, using the relationship between variables to generate features that may improve the performance of disease classification models. In order to capture information from different aspects of the data, this project uses a multiview learning approach, using Canonical Correlation Analysis (CCA), a technique that finds projections with maximum correlations between two data views. Data categories collected from the NHANES survey (1999-2014) are used as views to learn the multiview representations. The usefulness of the representations is demonstrated by applying them as features in a Diabetes classification task.
Explicit high-order feature interactions efficiently capture essential structural knowledge about the data of interest and have been used for constructing generative models. We present a supervised discriminative High-Order Parametric Embedding (HOPE) approach to data visualization and compression. Compared to deep embedding models with complicated deep architectures, HOPE generates more effective high-order feature mapping through an embarrassingly simple shallow model. Furthermore, two approaches to generating a small number of exemplars conveying high-order interactions to represent large-scale data sets are proposed. These exemplars in combination with the feature mapping learned by HOPE effectively capture essential data variations. Moreover, through HOPE, these exemplars are employed to increase the computational efficiency of kNN classification for fast information retrieval by thousands of times. For classification in two-dimensional embedding space on MNIST and USPS datasets, our shallow method HOPE with simple Sigmoid transformations significantly outperforms state-of-the-art supervised deep embedding models based on deep neural networks, and even achieved historically low test error rate of 0.65% in two-dimensional space on MNIST, which demonstrates the representational efficiency and power of supervised shallow models with high-order feature interactions.
In this paper, we propose a novel learning framework for the problem of domain transfer learning. We map the data of two domains to one single common space, and learn a classifier in this common space. Then we adapt the common classifier to the two domains by adding two adaptive functions to it respectively. In the common space, the target domain data points are weighted and matched to the target domain in term of distributions. The weighting terms of source domain data points and the target domain classification responses are also regularized by the local reconstruction coefficients. The novel transfer learning framework is evaluated over some benchmark cross-domain data sets, and it outperforms the existing state-of-the-art transfer learning methods.
When working with three-dimensional data, choice of representation is key. We explore voxel-based models, and present evidence for the viability of voxellated representations in applications including shape modeling and object classification. Our key contributions are methods for training voxel-based variational autoencoders, a user interface for exploring the latent space learned by the autoencoder, and a deep convolutional neural network architecture for object classification. We address challenges unique to voxel-based representations, and empirically evaluate our models on the ModelNet benchmark, where we demonstrate a 51.5% relative improvement in the state of the art for object classification.
Following the seminal idea of Tukey, data depth is a function that measures how close an arbitrary point of the space is located to an implicitly defined center of a data cloud. Having undergone theoretical and computational developments, it is now employed in numerous applications with classification being the most popular one. The R-package ddalpha is a software directed to fuse experience of the applicant with recent achievements in the area of data depth and depth-based classification. ddalpha provides an implementation for exact and approximate computation of most reasonable and widely applied notions of data depth. These can be further used in the depth-based multivariate and functional classifiers implemented in the package, where the $DD\alpha$-procedure is in the main focus. The package is expandable with user-defined custom depth methods and separators. The implemented functions for depth visualization and the built-in benchmark procedures may also serve to provide insights into the geometry of the data and the quality of pattern recognition.
The $k$-nearest neighbor classification method ($k$-NNC) is one of the simplest nonparametric classification methods. The mutual $k$-NN classification method (M$k$NNC) is a variant of $k$-NNC based on mutual neighborship. We propose another variant of $k$-NNC, the symmetric $k$-NN classification method (S$k$NNC) based on both mutual neighborship and one-sided neighborship. The performance of M$k$NNC and S$k$NNC depends on the parameter $k$ as the one of $k$-NNC does. We propose the ways how M$k$NN and S$k$NN classification can be performed based on Bayesian mutual and symmetric $k$-NN regression methods with the selection schemes for the parameter $k$. Bayesian mutual and symmetric $k$-NN regression methods are based on Gaussian process models, and it turns out that they can do M$k$NN and S$k$NN classification with new encodings of target values (class labels). The simulation results show that the proposed methods are better than or comparable to $k$-NNC, M$k$NNC and S$k$NNC with the parameter $k$ selected by the leave-one-out cross validation method not only for an artificial data set but also for real world data sets.
This report describes our submissions to Task2 and Task3 of the DCASE 2016 challenge. The systems aim at dealing with the detection of overlapping audio events in continuous streams, where the detectors are based on random decision forests. The proposed forests are jointly trained for classification and regression simultaneously. Initially, the training is classification-oriented to encourage the trees to select discriminative features from overlapping mixtures to separate positive audio segments from the negative ones. The regression phase is then carried out to let the positive audio segments vote for the event onsets and offsets, and therefore model the temporal structure of audio events. One random decision forest is specifically trained for each event category of interest. Experimental results on the development data show that our systems significantly outperform the baseline on the Task2 evaluation while they are inferior to the baseline in the Task3 evaluation.