Abstract: Receiver Operating Characteristic (ROC) curves are plots of true positive rate versus false positive rate which are used to evaluate binary classification algorithms. Because the Area Under the Curve (AUC) is a constant function of the predicted values, learning algorithms instead optimize convex relaxations which involve a sum over all pairs of labeled positive and negative examples. Naive learning algorithms compute the gradient in quadratic time, which is too slow for learning using large batch sizes. We propose a new functional representation of the square loss and squared hinge loss, which results in algorithms that compute the gradient in either linear or log-linear time, and makes it possible to use gradient descent learning with large batch sizes. Abstract: Arunachalam and de Wolf (2018) showed that the sample complexity of quantum batch learning of boolean functions, in the realizable and agnostic settings, has the same form and order as the corresponding classical sample complexities.

Landslides are notoriously difficult to predict because numerous spatially and temporally varying factors contribute to slope stability. Artificial neural networks (ANN) have been shown to improve prediction accuracy but are largely uninterpretable. Here we introduce an additive ANN optimization framework to assess landslide susceptibility, as well as dataset division and outcome interpretation techniques. We refer to our approach, which features full interpretability, high accuracy, high generalizability and low model complexity, as superposable neural network (SNN) optimization. We validate our approach by training models on landslide inventory from three different easternmost Himalaya regions. Our SNN outperformed physically-based and statistical models and achieved similar performance to state-of-the-art deep neural networks. The SNN models found the product of slope and precipitation and hillslope aspect to be important primary contributors to high landslide susceptibility, which highlights the importance of strong slope-climate couplings, along with microclimates, on landslide occurrences.

Intent classification is a fundamental task in the spoken language understanding field that has recently gained the attention of the scientific community, mainly because of the feasibility of approaching it with end-to-end neural models. In this way, avoiding using intermediate steps, i.e. automatic speech recognition, is possible, thus the propagation of errors due to background noise, spontaneous speech, speaking styles of users, etc. Towards the development of solutions applicable in real scenarios, it is interesting to investigate how environmental noise and related noise reduction techniques to address the intent classification task with end-to-end neural models. In this paper, we experiment with a noisy version of the fluent speech command data set, combining the intent classifier with a time-domain speech enhancement solution based on Wave-U-Net and considering different training strategies. Experimental results reveal that, for this task, the use of speech enhancement greatly improves the classification accuracy in noisy conditions, in particular when the classification model is trained on enhanced signals.

Past studies have illustrated the prevalence of UI dark patterns, or user interfaces that can lead end-users toward (unknowingly) taking actions that they may not have intended. Such deceptive UI designs can result in adverse effects on end users, such as oversharing personal information or financial loss. While significant research progress has been made toward the development of dark pattern taxonomies, developers and users currently lack guidance to help recognize, avoid, and navigate these often subtle design motifs. However, automated recognition of dark patterns is a challenging task, as the instantiation of a single type of pattern can take many forms, leading to significant variability. In this paper, we take the first step toward understanding the extent to which common UI dark patterns can be automatically recognized in modern software applications. To do this, we introduce AidUI, a novel automated approach that uses computer vision and natural language processing techniques to recognize a set of visual and textual cues in application screenshots that signify the presence of ten unique UI dark patterns, allowing for their detection, classification, and localization. To evaluate our approach, we have constructed ContextDP, the current largest dataset of fully-localized UI dark patterns that spans 175 mobile and 83 web UI screenshots containing 301 dark pattern instances. The results of our evaluation illustrate that \AidUI achieves an overall precision of 0.66, recall of 0.67, F1-score of 0.65 in detecting dark pattern instances, reports few false positives, and is able to localize detected patterns with an IoU score of ~0.84. Furthermore, a significant subset of our studied dark patterns can be detected quite reliably (F1 score of over 0.82), and future research directions may allow for improved detection of additional patterns.

In recent years fairness in machine learning (ML) has emerged as a highly active area of research and development. Most define fairness in simple terms, where fairness means reducing gaps in performance or outcomes between demographic groups while preserving as much of the accuracy of the original system as possible. This oversimplification of equality through fairness measures is troubling. Many current fairness measures suffer from both fairness and performance degradation, or "levelling down," where fairness is achieved by making every group worse off, or by bringing better performing groups down to the level of the worst off. When fairness can only be achieved by making everyone worse off in material or relational terms through injuries of stigma, loss of solidarity, unequal concern, and missed opportunities for substantive equality, something would appear to have gone wrong in translating the vague concept of 'fairness' into practice. This paper examines the causes and prevalence of levelling down across fairML, and explore possible justifications and criticisms based on philosophical and legal theories of equality and distributive justice, as well as equality law jurisprudence. We find that fairML does not currently engage in the type of measurement, reporting, or analysis necessary to justify levelling down in practice. We propose a first step towards substantive equality in fairML: "levelling up" systems by design through enforcement of minimum acceptable harm thresholds, or "minimum rate constraints," as fairness constraints. We likewise propose an alternative harms-based framework to counter the oversimplified egalitarian framing currently dominant in the field and push future discussion more towards substantive equality opportunities and away from strict egalitarianism by default. N.B. Shortened abstract, see paper for full abstract.

Several generic methods have recently been developed for change detection in heterogeneous remote sensing data, such as images from synthetic aperture radar (SAR) and multispectral radiometers. However, these are not well suited to detect weak signatures of certain disturbances of ecological systems. To resolve this problem we propose a new approach based on image-to-image translation and one-class classification (OCC). We aim to map forest mortality caused by an outbreak of geometrid moths in a sparsely forested forest-tundra ecotone using multisource satellite images. The images preceding and following the event are collected by Landsat-5 and RADARSAT-2, respectively. Using a recent deep learning method for change-aware image translation, we compute difference images in both satellites' respective domains. These differences are stacked with the original pre- and post-event images and passed to an OCC trained on a small sample from the targeted change class. The classifier produces a credible map of the complex pattern of forest mortality.

The credit card has become the most popular payment method for both online and offline transactions. The necessity to create a fraud detection algorithm to precisely identify and stop fraudulent activity arises as a result of both the development of technology and the rise in fraud cases. This paper implements the random forest (RF) algorithm to solve the issue in the hand. A dataset of credit card transactions was used in this study. The main problem when dealing with credit card fraud detection is the imbalanced dataset in which most of the transaction are non-fraud ones. To overcome the problem of the imbalanced dataset, the synthetic minority over-sampling technique (SMOTE) was used. Implementing the hyperparameters technique to enhance the performance of the random forest classifier. The results showed that the RF classifier gained an accuracy of 98% and about 98% of F1-score value, which is promising. We also believe that our model is relatively easy to apply and can overcome the issue of imbalanced data for fraud detection applications.

As the number of automatic tools based on machine learning (ML) and resting-state electroencephalography (rs-EEG) for Parkinson's disease (PD) detection keeps growing, the assessment of possible exacerbation of health disparities by means of fairness and bias analysis becomes more relevant. Protected attributes, such as gender, play an important role in PD diagnosis development. However, analysis of sub-group populations stemming from different genders is seldom taken into consideration in ML models' development or the performance assessment for PD detection. In this work, we perform a systematic analysis of the detection ability for gender sub-groups in a multi-center setting of a previously developed ML algorithm based on power spectral density (PSD) features of rs-EEG. We find significant differences in the PD detection ability for males and females at testing time (80.5% vs. 63.7% accuracy) and significantly higher activity for a set of parietal and frontal EEG channels and frequency sub-bands for PD and non-PD males that might explain the differences in the PD detection ability for the gender sub-groups.

The aggravating effects of climate change and the growing population in hurricane-prone areas escalate the challenges in large-scale hurricane evacuations. While hurricane preparedness and response strategies vastly rely on the accuracy and timeliness of the predicted households' evacuation decisions, current studies featuring psychological-driven linear models leave some significant limitations in practice. Hence, the present study proposes a new methodology for predicting households' evacuation decisions constructed by easily accessible demographic and resource-related predictors compared to current models with a high reliance on psychological factors. Meanwhile, an enhanced logistic regression (ELR) model that could automatically account for nonlinearities (i.e., univariate and bivariate threshold effects) by an interpretable machine learning approach is developed to secure the accuracy of the results. Specifically, low-depth decision trees are selected for nonlinearity detection to identify the critical thresholds, build a transparent model structure, and solidify the robustness. Then, an empirical dataset collected after Hurricanes Katrina and Rita is hired to examine the practicability of the new methodology. The results indicate that the enhanced logistic regression (ELR) model has the most convincing performance in explaining the variation of the households' evacuation decision in model fit and prediction capability compared to previous linear models. It suggests that the proposed methodology could provide a new tool and framework for the emergency management authorities to improve the estimation of evacuation traffic demands in a timely and accurate manner.

In recent decades, machine learning has provided valuable models and algorithms for processing and extracting knowledge from time-series surveys. Different classifiers have been proposed and performed to an excellent standard. Nevertheless, few papers have tackled the data shift problem in labeled training sets, which occurs when there is a mismatch between the data distribution in the training set and the testing set. This drawback can damage the prediction performance in unseen data. Consequently, we propose a scalable and easily adaptable approach based on an informative regularization and an ad-hoc training procedure to mitigate the shift problem during the training of a multi-layer perceptron for RR Lyrae classification. We collect ranges for characteristic features to construct a symbolic representation of prior knowledge, which was used to model the informative regularizer component. Simultaneously, we design a two-step back-propagation algorithm to integrate this knowledge into the neural network, whereby one step is applied in each epoch to minimize classification error, while another is applied to ensure regularization. Our algorithm defines a subset of parameters (a mask) for each loss function. This approach handles the forgetting effect, which stems from a trade-off between these loss functions (learning from data versus learning expert knowledge) during training. Experiments were conducted using recently proposed shifted benchmark sets for RR Lyrae stars, outperforming baseline models by up to 3\% through a more reliable classifier. Our method provides a new path to incorporate knowledge from characteristic features into artificial neural networks to manage the underlying data shift problem.