In this work, we examine the process of Tropical Polynomial Division, a geometric method which seeks to emulate the division of regular polynomials, when applied to those of the max-plus semiring. This is done via the approximation of the Newton Polytope of the dividend polynomial by that of the divisor. This process is afterwards generalized and applied in the context of neural networks with ReLU activations. In particular, we make use of the intuition it provides, in order to minimize a two-layer fully connected network, trained for a binary classification problem. This method is later evaluated on a variety of experiments, demonstrating its capability to approximate a network, with minimal loss in performance.
Deep learning-based construction-site image analysis has recently made great progress with regard to accuracy and speed, but it requires a large amount of data. Acquiring sufficient amount of labeled construction-image data is a prerequisite for deep learning-based construction-image recognition and requires considerable time and effort. In this paper, we propose a "data augmentation" scheme based on generative adversarial networks (GANs) for construction-equipment classification. The proposed method combines a GAN and additional "adversarial training" to stably perform "data augmentation" for construction equipment. The "data augmentation" was verified via binary classification experiments involving excavator images, and the average accuracy improvement was 4.094%. In the experiment, three image sizes (32-32-3, 64-64-3, and 128-128-3) and 120, 240, and 480 training samples were used to demonstrate the robustness of the proposed method. These results demonstrated that the proposed method can effectively and reliably generate construction-equipment images and train deep learning-based classifiers for construction equipment.
Growing number of network devices and services have led to increasing demand for protective measures as hackers launch attacks to paralyze or steal information from victim systems. Intrusion Detection System (IDS) is one of the essential elements of network perimeter security which detects the attacks by inspecting network traffic packets or operating system logs. While existing works demonstrated effectiveness of various machine learning techniques, only few of them utilized the time-series information of network traffic data. Also, categorical information has not been included in neural network based approaches. In this paper, we propose network intrusion detection models based on sequential information using long short-term memory (LSTM) network and categorical information using the embedding technique. We have experimented the models with UNSW-NB15, which is a comprehensive network traffic dataset. The experiment results confirm that the proposed method improve the performance, observing binary classification accuracy of 99.72\%.
We study binary classification algorithms for which the prediction on any point is not too sensitive to individual examples in the dataset. Specifically, we consider the notions of uniform stability (Bousquet and Elisseeff, 2001) and prediction privacy (Dwork and Feldman, 2018). Previous work on these notions shows how they can be achieved in the standard PAC model via simple aggregation of models trained on disjoint subsets of data. Unfortunately, this approach leads to a significant overhead in terms of sample complexity. Here we demonstrate several general approaches to stable and private prediction that either eliminate or significantly reduce the overhead. Specifically, we demonstrate that for any class $C$ of VC dimension $d$ there exists a $\gamma$-uniformly stable algorithm for learning $C$ with excess error $\alpha$ using $\tilde O(d/(\alpha\gamma) + d/\alpha^2)$ samples. We also show that this bound is nearly tight. For $\epsilon$-differentially private prediction we give two new algorithms: one using $\tilde O(d/(\alpha^2\epsilon))$ samples and another one using $\tilde O(d^2/(\alpha\epsilon) + d/\alpha^2)$ samples. The best previously known bounds for these problems are $O(d/(\alpha^2\gamma))$ and $O(d/(\alpha^3\epsilon))$, respectively.
Nowadays, Vector-Borne Diseases (VBDs) raise a severe threat for public health, accounting for a considerable amount of human illnesses. Recently, several surveillance plans have been put in place for limiting the spread of such diseases, typically involving on-field measurements. Such a systematic and effective plan still misses, due to the high costs and efforts required for implementing it. Ideally, any attempt in this field should consider the triangle vectors-host-pathogen, which is strictly linked to the environmental and climatic conditions. In this paper, we exploit satellite imagery from Sentinel-2 mission, as we believe they encode the environmental factors responsible for the vector's spread. Our analysis - conducted in a data-driver fashion - couples spectral images with ground-truth information on the abundance of Culicoides imicola. In this respect, we frame our task as a binary classification problem, underpinning Convolutional Neural Networks (CNNs) as being able to learn useful representation from multi-band images. Additionally, we provide a multi-instance variant, aimed at extracting temporal patterns from a short sequence of spectral images. Experiments show promising results, providing the foundations for novel supportive tools, which could depict where surveillance and prevention measures could be prioritized.
Often the development of novel functional peptides is not amenable to high throughput or purely computational screening methods. Peptides must be synthesized one at a time in a process that does not generate large amounts of data. One way this method can be improved is by ensuring that each experiment provides the best improvement in both peptide properties and predictive modeling accuracy. Here, we study the effectiveness of active learning, optimizing experiment order, and meta-learning, transferring knowledge between contexts, to reduce the number of experiments necessary to build a predictive model. We present a multi-task benchmark database of peptides designed to advance these methods for experimental design. Each task is binary classification of peptides represented as a sequence string. We find neither active learning method tested to be better than random choice. The meta-learning method Reptile was found to improve average accuracy across datasets. Combining meta-learning with active learning offers inconsistent benefits.
The spectacular expansion of the Internet has led to the development of a new research problem in the field of natural language processing: automatic toxic comment detection, since many countries prohibit hate speech in public media. There is no clear and formal definition of hate, offensive, toxic and abusive speeches. In this article, we put all these terms under the umbrella of "toxic" speech. The contribution of this paper is the design of binary classification and regression-based approaches aiming to predict whether a comment is toxic or not. We compare different unsupervised word representations and different DNN based classifiers. Moreover, we study the robustness of the proposed approaches to adversarial attacks by adding one (healthy or toxic) word. We evaluate the proposed methodology on the English Wikipedia Detox corpus. Our experiments show that using BERT fine-tuning outperforms feature-based BERT, Mikolov's and fastText representations with different DNN classifiers.
Single Image Super Resolution (SISR) is the process of mapping a low-resolution image to a high resolution image. This inherently has applications in remote sensing as a way to increase the spatial resolution in satellite imagery. This suggests a possible improvement to automated target recognition in image classification and object detection. We explore the effect that different training sets have on SISR with the network, Super Resolution Generative Adversarial Network (SRGAN). We train 5 SRGANs on different land-use classes (e.g. agriculture, cities, ports) and test them on the same unseen dataset. We attempt to find the qualitative and quantitative differences in SISR, binary classification, and object detection performance. We find that curated training sets that contain objects in the test ontology perform better on both computer vision tasks while having a complex distribution of images allows object detection models to perform better. However, Super Resolution (SR) might not be beneficial to certain problems and will see a diminishing amount of returns for datasets that are closer to being solved.
We consider the problem of learning linear classifiers when both features and labels are binary. In addition, the features are noisy, i.e., they could be flipped with an unknown probability. In Sy-De attribute noise model, where all features could be noisy together with same probability, we show that $0$-$1$ loss ($l_{0-1}$) need not be robust but a popular surrogate, squared loss ($l_{sq}$) is. In Asy-In attribute noise model, we prove that $l_{0-1}$ is robust for any distribution over 2 dimensional feature space. However, due to computational intractability of $l_{0-1}$, we resort to $l_{sq}$ and observe that it need not be Asy-In noise robust. Our empirical results support Sy-De robustness of squared loss for low to moderate noise rates.
A common problem of the real-world data sets is the class imbalance, which can significantly affect the classification abilities of classifiers. Numerous methods have been proposed to cope with this problem; however, even state-of-the-art methods offer a limited improvement (if any) for data sets with critically under-represented minority classes. For such problematic cases, an "outside the box" solution is required. Therefore, we propose a novel technique, called enrichment, which uses the information (observations) from the external data set(s). We present three approaches to implement enrichment technique: (1) selecting observations randomly, (2) iteratively choosing observations that improve the classification result, (3) adding observations that help the classifier to determine the border between classes better. We then thoroughly analyze developed solutions on ten real-world data sets to experimentally validate their usefulness. On average, our best approach improves the classification quality by 27\%, and in the best case, by outstanding 66\%. We also compare our technique with the universally applicable state-of-the-art methods. We find that our technique surpasses the existing methods performing, on average, 21\% better. The advantage is especially noticeable for the smallest data sets, for which existing methods failed, while our solutions achieved the best results. Additionally, our technique applies to both the multi-class and binary classification tasks. It can also be combined with other techniques dealing with the class imbalance problem.
We present a selective sampling method designed to accelerate the training of deep neural networks. To this end, we introduce a novel measurement, the minimal margin score (MMS), which measures the minimal amount of displacement an input should take until its predicted classification is switched. For multi-class linear classification, the MMS measure is a natural generalization of the margin-based selection criterion, which was thoroughly studied in the binary classification setting. In addition, the MMS measure provides an interesting insight into the progress of the training process and can be useful for designing and monitoring new training regimes. Empirically we demonstrate a substantial acceleration when training commonly used deep neural network architectures for popular image classification tasks. The efficiency of our method is compared against the standard training procedures, and against commonly used selective sampling alternatives: Hard negative mining selection, and Entropy-based selection. Finally, we demonstrate an additional speedup when we adopt a more aggressive learning drop regime while using the MMS selective sampling method.
A key challenge in crowdsourcing is inferring the ground truth from noisy and unreliable data. To do so, existing approaches rely on collecting redundant information from the crowd, and aggregating it with some probabilistic method. However, oftentimes such methods are computationally inefficient, are restricted to some specific settings, or lack theoretical guarantees. In this paper, we revisit the problem of binary classification from crowdsourced data. Specifically we propose Streaming Bayesian Inference for Crowdsourcing (SBIC), a new algorithm that does not suffer from any of these limitations. First, SBIC has low complexity and can be used in a real-time online setting. Second, SBIC has the same accuracy as the best state-of-the-art algorithms in all settings. Third, SBIC has provable asymptotic guarantees both in the online and offline settings.
Although kernel methods are widely used in many learning problems, they have poor scalability to large datasets. To address this problem, sketching and stochastic gradient methods are the most commonly used techniques to derive efficient large-scale learning algorithms. In this study, we consider solving a binary classification problem using random features and stochastic gradient descent. In recent research, an exponential convergence rate of the expected classification error under the strong low-noise condition has been shown. We extend these analyses to a random features setting, analyzing the error induced by the approximation of random features in terms of the distance between the generated hypothesis including population risk minimizers and empirical risk minimizers when using general Lipschitz loss functions, to show that an exponential convergence of the expected classification error is achieved even if random features approximation is applied. Additionally, we demonstrate that the convergence rate does not depend on the number of features and there is a significant computational benefit in using random features in classification problems because of the strong low-noise condition.
In this work, we explore the possibility of decoding Imagined Speech brain waves using machine learning techniques. We propose a covariance matrix of Electroencephalogram channels as input features, projection to tangent space of covariance matrices for obtaining vectors from covariance matrices, principal component analysis for dimension reduction of vectors, an artificial feed-forward neural network as a classification model and bootstrap aggregation for creating an ensemble of neural network models. After the classification, two different Finite State Machines are designed that create an interface for controlling a computer system using an Imagined Speech-based BCI system. The proposed approach is able to decode the Imagined Speech signal with a maximum mean classification accuracy of 85% on binary classification task of one long word and a short word. We also show that our proposed approach is able to differentiate between imagined speech brain signals and rest state brain signals with maximum mean classification accuracy of 94%. We compared our proposed method with other approaches for decoding imagined speech and show that our approach performs equivalent to the state of the art approach on decoding long vs. short words and outperforms it significantly on the other two tasks of decoding three short words and three vowels with an average margin of 11% and 9%, respectively. We also obtain an information transfer rate of 21-bits-per-minute when using an IS based system to operate a computer. These results show that the proposed approach is able to decode a wide variety of imagined speech signals without any human-designed features.
The labels in medical diagnosis task are usually discrete and successively distributed. For example, the Diabetic Retinopathy Diagnosis (DR) involves five health risk levels: no DR (0), mild DR (1), moderate DR (2), severe DR (3) and proliferative DR (4). This labeling system is common for medical disease. Previous methods usually construct a multi-binary-classification task or propose some re-parameter schemes in the output unit. In this paper, we target on this task from the perspective of loss function. More specifically, the Wasserstein distance is utilized as an alternative, explicitly incorporating the inter-class correlations by pre-defining its ground metric. Then, the ground metric which serves as a linear, convex or concave increasing function w.r.t. the Euclidean distance in a line is explored from an optimization perspective. Meanwhile, this paper also proposes of constructing the smoothed target labels that model the inlier and outlier noises by using a unimodal-uniform mixture distribution. Different from the one-hot setting, the smoothed label endues the computation of Wasserstein distance with more challenging features. With either one-hot or smoothed target label, this paper systematically concludes the practical closed-form solution. We evaluate our method on several medical diagnosis tasks (e.g., Diabetic Retinopathy and Ultrasound Breast dataset) and achieve state-of-the-art performance.
In this paper, we proposed a general framework for data poisoning attacks to graph-based semi-supervised learning (G-SSL). In this framework, we first unify different tasks, goals, and constraints into a single formula for data poisoning attack in G-SSL, then we propose two specialized algorithms to efficiently solve two important cases --- poisoning regression tasks under $\ell_2$-norm constraint and classification tasks under $\ell_0$-norm constraint. In the former case, we transform it into a non-convex trust region problem and show that our gradient-based algorithm with delicate initialization and update scheme finds the (globally) optimal perturbation. For the latter case, although it is an NP-hard integer programming problem, we propose a probabilistic solver that works much better than the classical greedy method. Lastly, we test our framework on real datasets and evaluate the robustness of G-SSL algorithms. For instance, on the MNIST binary classification problem (50000 training data with 50 labeled), flipping two labeled data is enough to make the model perform like random guess (around 50\% error).
Objectives: To compare breast density (BD) assessment provided by an automated BD evaluator (ABDE) with that provided by a panel of experienced breast radiologists, on a multivendor dataset. Methods: Twenty-one radiologists assessed 613 screening/diagnostic digital mammograms from 9 centers and 6 different vendors, using the BI-RADS a, b, c, and d density classification. The same mammograms were also evaluated by an ABDE providing the ratio between fibroglandular and total breast area on a continuous scale and, automatically, the BI-RADS score. Panel majority report (PMR) was used as reference standard. Agreement (k) and accuracy (proportion of cases correctly classified) were calculated for binary (BI-RADS a-b versus c-d) and 4-class classification. Results: While the agreement of individual radiologists with PMR ranged from k=0.483 to k=0.885, the ABDE correctly classified 563/613 mammograms (92%). A substantial agreement for binary classification was found for individual reader pairs (k=0.620, standard deviation [SD]=0.140), individual versus PMR (k=0.736, SD=0.117), and individual versus ABDE (k=0.674, SD=0.095). Agreement between ABDE and PMR was almost perfect (k=0.831). Conclusions: The ABDE showed an almost perfect agreement with a 21-radiologist panel in binary BD classification on a multivendor dataset, earning a chance as a reproducible alternative to visual evaluation.
Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence. With neural networks, calibration can be improved by temperature scaling, a method to learn a single corrective multiplicative factor for inputs to the last softmax layer. On non-neural models the existing methods apply binary calibration in a pairwise or one-vs-rest fashion. We propose a natively multiclass calibration method applicable to classifiers from any model class, derived from Dirichlet distributions and generalising the beta calibration method from binary classification. It is easily implemented with neural nets since it is equivalent to log-transforming the uncalibrated probabilities, followed by one linear layer and softmax. Experiments demonstrate improved probabilistic predictions according to multiple measures (confidence-ECE, classwise-ECE, log-loss, Brier score) across a wide range of datasets and classifiers. Parameters of the learned Dirichlet calibration map provide insights to the biases in the uncalibrated model.
Diagnostic procedures for ASD (autism spectrum disorder) involve semi-naturalistic interactions between the child and a clinician. Computational methods to analyze these sessions require an end-to-end speech and language processing pipeline that go from raw audio to clinically-meaningful behavioral features. An important component of this pipeline is the ability to automatically detect who is speaking when i.e., perform child-adult speaker classification. This binary classification task is often confounded due to variability associated with the participants' speech and background conditions. Further, scarcity of training data often restricts direct application of conventional deep learning methods. In this work, we address two major sources of variability - age of the child and data source collection location - using domain adversarial learning which does not require labeled target domain data. We use two methods, generative adversarial training with inverted label loss and gradient reversal layer to learn speaker embeddings invariant to the above sources of variability, and analyze different conditions under which the proposed techniques improve over conventional learning methods. Using a large corpus of ADOS-2 (autism diagnostic observation schedule, 2nd edition) sessions, we demonstrate upto 13.45% and 6.44% relative improvements over conventional learning methods.
Convolutional neural networks can be trained to perform histology slide classification using weak annotations with multiple instance learning (MIL). However, given the paucity of labeled histology data, direct application of MIL can easily suffer from overfitting and the network is unable to learn rich feature representations due to the weak supervisory signal. We propose to overcome such limitations with a two-stage semi-supervised approach that combines the power of data-efficient self-supervised feature learning via contrastive predictive coding (CPC) and the interpretability and flexibility of regularized attention-based MIL. We apply our two-stage CPC + MIL semi-supervised pipeline to the binary classification of breast cancer histology images. Across five random splits, we report state-of-the-art performance with a mean validation accuracy of 95% and an area under the ROC curve of 0.968. We further evaluate the quality of features learned via CPC relative to simple transfer learning and show that strong classification performance using CPC features can be efficiently leveraged under the MIL framework even with the feature encoder frozen.