Largest theoretical contribution to Neural Networks comes from VC Dimension which characterizes the sample complexity of classification model in a probabilistic view and are widely used to study the generalization error. So far in the literature the VC Dimension has only been used to approximate the generalization error bounds on different Neural Network architectures. VC Dimension has not yet been implicitly or explicitly stated to fix the network size which is important as the wrong configuration could lead to high computation effort in training and leads to over fitting. So there is a need to bound these units so that task can be computed with only sufficient number of parameters. For binary classification tasks shallow networks are used as they have universal approximation property and it is enough to size the hidden layer width for such networks. The paper brings out a theoretical justification on required attribute size and its corresponding hidden layer dimension for a given sample set that gives an optimal binary classification results with minimum training complexity in a single layered feed forward network framework. The paper also establishes proof on the existence of bounds on the width of the hidden layer and its range subjected to certain conditions. Findings in this paper are experimentally analyzed on three different dataset using Mathlab 2018 (b) software.
The explosion of time series data in recent years has brought a flourish of new time series analysis methods, for forecasting, clustering, classification and other tasks. The evaluation of these new methods requires either collecting or simulating a diverse set of time series benchmarking data to enable reliable comparisons against alternative approaches. We propose GeneRAting TIme Series with diverse and controllable characteristics, named GRATIS, with the use of mixture autoregressive (MAR) models. We simulate sets of time series using MAR models and investigate the diversity and coverage of the generated time series in a time series feature space. By tuning the parameters of the MAR models, GRATIS is also able to efficiently generate new time series with controllable features. In general, as a costless surrogate to the traditional data collection approach, GRATIS can be used as an evaluation tool for tasks such as time series forecasting and classification. We illustrate the usefulness of our time series generation process through a time series forecasting application.
Data science relies on pipelines that are organized in the form of interdependent computational steps. Each step consists of various candidate algorithms that maybe used for performing a particular function. Each algorithm consists of several hyperparameters. Algorithms and hyperparameters must be optimized as a whole to produce the best performance. Typical machine learning pipelines typically consist of complex algorithms in each of the steps. Not only is the selection process combinatorial, but it is also important to interpret and understand the pipelines. We propose a method to quantify the importance of different layers in the pipeline, by computing an error contribution relative to an agnostic choice of algorithms in that layer. We demonstrate our methodology on image classification pipelines. The agnostic methodology quantifies the error contributions from the computational steps, algorithms and hyperparameters in the image classification pipeline. We show that algorithm selection and hyper-parameter optimization methods can be used to quantify the error contribution and that random search is able to quantify the contribution more accurately than Bayesian optimization. This methodology can be used by domain experts to understand machine learning and data analysis pipelines in terms of their individual components, which can help in prioritizing different components of the pipeline.
We present several techniques to tackle the mismatch in class distributions between training and test data in the Contextual Emotion Detection task of SemEval 2019, by extending the existing methods for class imbalance problem. Reducing the distance between the distribution of prediction and ground truth, they consistently show positive effects on the performance. Also we propose a novel neural architecture which utilizes representation of overall context as well as of each utterance. The combination of the methods and the models achieved micro F1 score of about 0.766 on the final evaluation.
Two-stream architecture have shown strong performance in video classification task. The key idea is to learn spatio-temporal features by fusing convolutional networks spatially and temporally. However, there are some problems within such architecture. First, it relies on optical flow to model temporal information, which are often expensive to compute and store. Second, it has limited ability to capture details and local context information for video data. Third, it lacks explicit semantic guidance that greatly decrease the classification performance. In this paper, we proposed a new two-stream based deep framework for video classification to discover spatial and temporal information only from RGB frames, moreover, the multi-scale pyramid attention (MPA) layer and the semantic adversarial learning (SAL) module is introduced and integrated in our framework. The MPA enables the network capturing global and local feature to generate a comprehensive representation for video, and the SAL can make this representation gradually approximate to the real video semantics in an adversarial manner. Experimental results on two public benchmarks demonstrate our proposed methods achieves state-of-the-art results on standard video datasets.
This report examines the Pinned AUC metric introduced and highlights some of its limitations. Pinned AUC provides a threshold-agnostic measure of unintended bias in a classification model, inspired by the ROC-AUC metric. However, as we highlight in this report, there are ways that the metric can obscure different kinds of unintended biases when the underlying class distributions on which bias is being measured are not carefully controlled.
In electroencephalogram (EEG) signal processing, finding the appropriate information from a dataset has been a big challenge for successful signal classification. The feature selection methods make it possible to solve this problem; however, the method selection is still under investigation to find out which feature can perform the best to extract the most proper features of the signal to improve the classification performance. In this study, we use the genetic algorithm (GA), a heuristic searching algorithm, to find the optimum combination of the feature extraction methods and the classifiers, in the brain-computer interface (BCI) applications. A BCI system can be practical if and only if it performs with high accuracy and high speed alongside each other. In the proposed method, GA performs as a searching engine to find the best combination of the features and classifications. The features used here are Katz, Higuchi, Petrosian, Sevcik, and box-counting dimension (BCD) feature extraction methods. These features are applied to the wavelet subbands and are classified with four classifiers such as adaptive neuro-fuzzy inference system (ANFIS), fuzzy k-nearest neighbors (FKNN), support vector machine (SVM) and linear discriminant analysis (LDA). Due to the huge number of features, the GA optimization is used to find the features with the optimum fitness value (FV). Results reveal that Katz fractal feature estimation method with LDA classification has the best FV. Consequently, due to the low computation time of the first Daubechies wavelet transformation in comparison to the original signal, the final selected methods contain the fractal features of the first coefficient of the detail subbands.
This work proposes PatchNet, an automated tool based on hierarchical deep learning for classifying patches by extracting features from commit messages and code changes. PatchNet contains a deep hierarchical structure that mirrors the hierarchical and sequential structure of a code change, differentiating it from the existing deep learning models on source code. PatchNet provides several options allowing users to select parameters for the training process. The tool has been validated in the context of automatic identification of stable-relevant patches in the Linux kernel and is potentially applicable to automate other software engineering tasks that can be formulated as patch classification problems. A video demonstrating PatchNet is available at https://goo.gl/CZjG6X. The PatchNet implementation is available at https://github.com/hvdthong/PatchNetTool.
This work generalizes graph neural networks (GNNs) beyond those based on the Weisfeiler-Lehman (WL) algorithm, graph Laplacians, and diffusions. Our approach, denoted Relational Pooling (RP), draws from the theory of finite partial exchangeability to provide a framework with maximal representation power for graphs. RP can work with existing graph representation models and, somewhat counterintuitively, can make them even more powerful than the original WL isomorphism test. Additionally, RP allows architectures like Recurrent Neural Networks and Convolutional Neural Networks to be used in a theoretically sound approach for graph classification. We demonstrate improved performance of RP-based graph representations over state-of-the-art methods on a number of tasks.
The repeated community-wide reuse of test sets in popular benchmark problems raises doubts about the credibility of reported test-error rates. Verifying whether a learned model is overfitted to a test set is challenging as independent test sets drawn from the same data distribution are usually unavailable, while other test sets may introduce a distribution shift. We propose a new hypothesis test that uses only the original test data to detect overfitting. It utilizes a new unbiased error estimate that is based on adversarial examples generated from the test data and importance weighting. Overfitting is detected if this error estimate is sufficiently different from the original test error rate. We develop a specialized variant of our test for multiclass image classification, and apply it to testing overfitting of recent models to the popular ImageNet benchmark. Our method correctly indicates overfitting of the trained model to the training set, but is not able to detect any overfitting to the test set, in line with other recent work on this topic.
Feature generating networks face to the most important question, which is the fitting difference (inconsistence) of the distribution between the generated feature and the real data. This inconsistence further influence the performance of the networks model, because training samples from seen classes is disjointed with testing samples from unseen classes in zero-shot learning (ZSL). In generalization zero-shot learning (GZSL), testing samples come from not only seen classes but also unseen classes for closer to the practical situation. Therefore, most of feature generating networks difficultly obtain satisfactory performance for the challenging GZSL by adversarial learning the distribution of semantic classes. To alleviate the negative influence of this inconsistence for ZSL and GZSL, transfer feature generating networks with semantic classes structure (TFGNSCS) is proposed to construct networks model for improving the performance of ZSL and GZSL. TFGNSCS can not only consider the semantic structure relationship between seen and unseen classes, but also learn the difference of generating features by transferring classification model information from seen to unseen classes in networks. The proposed method can integrate the transfer loss, the classification loss and the Wasserstein distance loss to generate enough CNN features, on which softmax classifiers are trained for ZSL and GZSL. Experiments demonstrate that the performance of TFGNSCS outperforms that of the state of the arts on four challenging datasets, which are CUB,FLO,SUN, AWA in GZSL.
We investigate the performance of a machine learning classification technique, called the Parzen window, to mitigate the fiber nonlinearity in the context of dispersion managed and dispersion unmanaged systems. The technique is applied for detection at the receiver side, and deals with the non-Gaussian nonlinear effects by designing improved decision boundaries. We also propose a two-stage mitigation technique using digital back propagation and Parzen window for dispersion unmanaged systems. In this case, digital back propagation compensates for the deterministic nonlinearity and the Parzen window deals with the stochastic nonlinear signal-noise interactions, which are not taken into account by digital back propagation. A performance improvement up to 0:4 dB in terms of Q factor is observed.
Experiments searching for rare processes like neutrinoless double beta decay heavily rely on the identification of background events to reduce their background level and increase their sensitivity. We present a novel machine learning based method to recognize one of the most abundant classes of background events in these experiments. By combining a neural network for feature extraction with a smaller classification network, our method can be trained with only a small number of labeled events. To validate our method, we use signals from a broad-energy germanium detector irradiated with a $^{228}$Th gamma source. We find that it matches the performance of state-of-the-art algorithms commonly used for this detector type. However, it requires less tuning and calibration and shows potential to identify certain types of background events missed by other methods.
We introduce a probabilistic robustness measure for Bayesian Neural Networks (BNNs), defined as the probability that, given a test point, there exists a point within a bounded set such that the BNN prediction differs between the two. Such a measure can be used, for instance, to quantify the probability of the existence of adversarial examples. Building on statistical verification techniques for probabilistic models, we develop a framework that allows us to estimate probabilistic robustness for a BNN with statistical guarantees, i.e., with a priori error and confidence bounds. We provide experimental comparison for several approximate BNN inference techniques on image classification tasks associated to MNIST and a two-class subset of the GTSRB dataset. Our results enable quantification of uncertainty of BNN predictions in adversarial settings.
In Computer Vision, finding simple features is performed using classifiers called interest point (IP) detectors, which are often utilised to track features as the scene changes. For 2D based classifiers it has been intuitive to measure repeated point reliability using 2D metrics given the difficulty to establish ground truth beyond 2D. The aim is to bridge the gap between 2D classifiers and 3D environments, and improve performance analysis of 2D IP classification on 3D objects. This paper builds on existing work with 3D scanned and artificial models to test conventional 2D feature detectors with the assistance of virtualised 3D scenes. Virtual space depth is leveraged in tests to perform pre-selection of closest repeatable points in both 2D and 3D contexts before repeatability is measured. This more reliable ground truth is used to analyse testing configurations with a singular and 12 model dataset across affine transforms in x, y and z rotation, as well as x,y scaling with 9 well known IP detectors. The virtual scene's ground truth demonstrates that 3D pre-selection eliminates a large portion of false positives that are normally considered repeated in 2D configurations. The results indicate that 3D virtual environments can provide assistance in comparing the performance of conventional detectors when extending their applications to 3D environments, and can result in better classification of features when testing prospective classifiers' performance. A ROC based informedness measure also highlights tradeoffs in 2D/3D performance compared to conventional repeatability measures.
Clustering, like covariate selection for classification, is an important step to compress and interpret the data. However, clustering of covariates is often performed independently of the classification step, which can lead to undesirable clustering results that harm interpretability and compression rate. Therefore, we propose a method that can cluster covariates while taking into account class label information of samples. We formulate the problem as a convex optimization problem which uses both, a-priori similarity information between covariates, and information from class-labeled samples. Like ordinary convex clustering [Chi and Lange, 2015], the proposed method offers a unique global minima making it insensitive to initialization. In order to solve the convex problem, we propose a specialized alternating direction method of multipliers (ADMM), which scales up to several thousands of variables. Furthermore, in order to circumvent computationally expensive cross-validation, we propose a model selection criterion based on approximating the marginal likelihood. Experiments on synthetic and real data confirm the usefulness of the proposed clustering method and the selection criterion.
In this paper, a novel architecture of Recurrent Neural Network (RNN) is designed and experimented. The proposed RNN adopts a computational memory based on the concept of stigmergy. The basic principle of a Stigmergic Memory (SM) is that the activity of deposit/removal of a quantity in the SM stimulates the next activities of deposit/removal. Accordingly, subsequent SM activities tend to reinforce/weaken each other, generating a coherent coordination between the SM activities and the input temporal stimulus. We show that, in a problem of supervised classification, the SM encodes the temporal input in an emergent representational model, by coordinating the deposit, removal and classification activities. This study lays down a basic framework for the derivation of a SM-RNN. A formal ontology of SM is discussed, and the SM-RNN architecture is detailed. To appreciate the computational power of an SM-RNN, comparative NNs have been selected and trained to solve the MNIST handwritten digits recognition benchmark in its two variants: spatial (sequences of bitmap rows) and temporal (sequences of pen strokes).
This short paper presents the design decisions taken and challenges encountered in completing SemEval Task 6, which poses the problem of identifying and categorizing offensive language in tweets. Our proposed solutions explore Deep Learning techniques, Linear Support Vector classification and Random Forests to identify offensive tweets, to classify offenses as targeted or untargeted and eventually to identify the target subject type.
\ac{ML} helps us to recognize patterns from raw data. \ac{ML} is used in numerous domains i.e. biomedical, agricultural, food technology, etc. Despite recent technological advancements, there is still room for substantial improvement in prediction. Current \ac{ML} models are based on classical theories of probability and statistics, which can now be replaced by \ac{QT} with the aim of improving the effectiveness of \ac{ML}. In this paper, we propose the \ac{BCIQT} model, which outperforms the state of the art classification in terms of recall for every category.
Despite the widespread use of machine learning algorithms to solve problems of technological, economic, and social relevance, provable guarantees on the performance of these data-driven algorithms are critically lacking, especially when the data originates from unreliable sources and is transmitted over unprotected and easily accessible channels. In this paper we take an important step to bridge this gap and formally show that, in a quest to optimize their accuracy, binary classification algorithms -- including those based on machine-learning techniques -- inevitably become more sensitive to adversarial manipulation of the data. Further, for a given class of algorithms with the same complexity (i.e., number of classification boundaries), the fundamental tradeoff curve between accuracy and sensitivity depends solely on the statistics of the data, and cannot be improved by tuning the algorithm.