In developing natural language processing (NLP) models to detect toxic language (Arango et al., 2019; Schmidt and Wiegand, 2017; Vaidya et al., 2020), we typically assume that toxic language manifests in similar forms across different targeted groups. For example, HateCheck (Röttger et al., 2021) enumerates templatic patterns such as "I hate [GROUP]" that we expect detection models to handle robustly across groups. Moreover, we typically pool data across different demographic targets in model training in order to learn general patterns of linguistic toxicity across diverse demographic targets. However, the nature and form of toxic language used to target different demographic groups can vary quite markedly. Furthermore, an imbalanced distribution of different demographic groups in toxic language datasets risks over-fitting forms of toxic language most relevant to the majority group(s), potentially at the expense of systematically weaker model performance on minority group(s). For this reason, a "one-size-fits-all" modeling approach may yield sub-optimal performance and more specifically raise concerns of algorithmic fairness (Arango et al., 2019; Park et al., 2018; Sap et al., 2019). At the same time, radically siloing off datasets for each different demographic target group would prevent models from learning broader linguistic patterns of toxicity across different demographic groups targeted.

For more than half a century, vibratory bowl feeders have been the standard in automated assembly for singulation, orientation, and manipulation of small parts. Unfortunately, these feeders are expensive, noisy, and highly specialized on a single part design bases. We consider an alternative device and learning control method for singulation, orientation, and manipulation by means of seven fixed-position variable-energy solenoid impulse actuators located beneath a semi-rigid part supporting surface. Using computer vision to provide part pose information, we tested various machine learning (ML) algorithms to generate a control policy that selects the optimal actuator and actuation energy. Our manipulation test object is a 6-sided craps-style die. Using the most suitable ML algorithm, we were able to flip the die to any desired face 30.4\% of the time with a single impulse, and 51.3\% with two chosen impulses, versus a random policy succeeding 5.1\% of the time (that is, a randomly chosen impulse delivered by a randomly chosen solenoid).

Model distillation (Hinton et al., 2015) is a common framework for knowledge transfer, where knowledge learned by a "teacher model" is transferred to a "student model" via the teacher's predictions. Distillation is helpful because the teacher's predictions are a more useful guide for the student model than hard labels; this phenomenon has been explained by the teacher's predictions containing some useful "dark knowledge". Variants of model distillation have been proposed for, e.g., model compression (Hinton et al., 2015; Ba & Caruana, 2014; Polino et al., 2018; Kim et al., 2018; Sun et al., 2019) or training more accurate models (Zagoruyko & Komodakis, 2016; Xie et al., 2020). Within the privacy-preserving machine learning community, distillation has been adapted to protect the privacy of a training dataset (Papernot et al., 2016; Tang et al., 2022; Shejwalkar & Houmansadr, 2021; Mazzone et al., 2022). Many of these approaches rely on the intuition that distilling the teacher model serves as a privacy barrier that protects the teacher's training data. Informally, restricting the student to learn only from the teacher's predictions is a form of data minimization, which should result in less private information being fed into, and memorized by, the student. This privacy barrier around the teacher also allows the teacher model to be trained with strong, non-private, training approaches, improving both the teacher model's and student model's accuracy. Because model distillation does not provide a rigorous privacy guarantee (such as those offered by differential privacy (Dwork et al., 2006)), in our work we evaluate the empirical privacy provided by these

Out-of-distribution (OOD) detection is indispensable for safely deploying machine learning models in the wild. One of the key challenges is that models lack supervision signals from unknown data, and as a result, can produce overconfident predictions on OOD data. Recent work on outlier synthesis modeled the feature space as parametric Gaussian distribution, a strong and restrictive assumption that might not hold in reality. In this paper, we propose a novel framework, Non-Parametric Outlier Synthesis (NPOS), which generates artificial OOD training data and facilitates learning a reliable decision boundary between ID and OOD data. Importantly, our proposed synthesis approach does not make any distributional assumption on the ID embeddings, thereby offering strong flexibility and generality. We show that our synthesis approach can be mathematically interpreted as a rejection sampling framework. Extensive experiments show that NPOS can achieve superior OOD detection performance, outperforming the competitive rivals by a significant margin. Code is publicly available at https://github.com/deeplearning-wisc/npos.

Fingerprint-based identification systems achieve higher accuracy when a slap containing multiple fingerprints of a subject is used instead of a single fingerprint. However, segmenting or auto-localizing all fingerprints in a slap image is a challenging task due to the different orientations of fingerprints, noisy backgrounds, and the smaller size of fingertip components. The presence of slap images in a real-world dataset where one or more fingerprints are rotated makes it challenging for a biometric recognition system to localize and label the fingerprints automatically. Improper fingerprint localization and finger labeling errors lead to poor matching performance. In this paper, we introduce a method to generate arbitrary angled bounding boxes using a deep learning-based algorithm that precisely localizes and labels fingerprints from both axis-aligned and over-rotated slap images. We built a fingerprint segmentation model named CRFSEG (Clarkson Rotated Fingerprint segmentation Model) by updating the previously proposed CFSEG model which was based on traditional Faster R-CNN architecture [21]. CRFSEG improves upon the Faster R-CNN algorithm with arbitrarily angled bounding boxes that allow the CRFSEG to perform better in challenging slap images. After training the CRFSEG algorithm on a new dataset containing slap images collected from both adult and children subjects, our results suggest that the CRFSEG model was invariant across different age groups and can handle over-rotated slap images successfully. In the Combined dataset containing both normal and rotated images of adult and children subjects, we achieved a matching accuracy of 97.17%, which outperformed state-of-the-art VeriFinger (94.25%) and NFSEG segmentation systems (80.58%).

Respiratory rate (RR) is an important biomarker as RR changes can reflect severe medical events such as heart disease, lung disease, and sleep disorders. Unfortunately, standard manual RR counting is prone to human error and cannot be performed continuously. This study proposes a method for continuously estimating RR, RRWaveNet. The method is a compact end-to-end deep learning model which does not require feature engineering and can use low-cost raw photoplethysmography (PPG) as input signal. RRWaveNet was tested subject-independently and compared to baseline in four datasets (BIDMC, CapnoBase, WESAD, and SensAI) and using three window sizes (16, 32, and 64 seconds). RRWaveNet outperformed current state-of-the-art methods with mean absolute errors at optimal window size of 1.66 \pm 1.01, 1.59 \pm 1.08, 1.92 \pm 0.96 and 1.23 \pm 0.61 breaths per minute for each dataset. In remote monitoring settings, such as in the WESAD and SensAI datasets, we apply transfer learning to improve the performance using two other ICU datasets as pretraining datasets, reducing the MAE by up to 21$\%$. This shows that this model allows accurate and practical estimation of RR on affordable and wearable devices. Our study also shows feasibility of remote RR monitoring in the context of telemedicine and at home.

pystacked implements stacked generalization (Wolpert, 1992) for regression and binary classification via Python's scikit-learn. Stacking combines multiple supervised machine learners -- the "base" or "level-0" learners -- into a single learner. The currently supported base learners include regularized regression, random forest, gradient boosted trees, support vector machines, and feed-forward neural nets (multi-layer perceptron). pystacked can also be used with as a `regular' machine learning program to fit a single base learner and, thus, provides an easy-to-use API for scikit-learn's machine learning algorithms.

We propose a new strategy for anomaly detection at the LHC based on unsupervised quantum machine learning algorithms. To accommodate the constraints on the problem size dictated by the limitations of current quantum hardware we develop a classical convolutional autoencoder. The designed quantum anomaly detection models, namely an unsupervised kernel machine and two clustering algorithms, are trained to find new-physics events in the latent representation of LHC data produced by the autoencoder. The performance of the quantum algorithms is benchmarked against classical counterparts on different new-physics scenarios and its dependence on the dimensionality of the latent space and the size of the training dataset is studied. For kernel-based anomaly detection, we identify a regime where the quantum model significantly outperforms its classical counterpart. An instance of the kernel machine is implemented on a quantum computer to verify its suitability for available hardware. We demonstrate that the observed consistent performance advantage is related to the inherent quantum properties of the circuit used.

Our goal is to improve reliability of Machine Learning (ML) systems deployed in the wild. ML models perform exceedingly well when test examples are similar to train examples. However, real-world applications are required to perform on any distribution of test examples. Current ML systems can fail silently on test examples with distribution shifts. In order to improve reliability of ML models due to covariate or domain shift, we propose algorithms that enable models to: (a) generalize to a larger family of test distributions, (b) evaluate accuracy under distribution shifts, (c) adapt to a target distribution. We study causes of impaired robustness to domain shifts and present algorithms for training domain robust models. A key source of model brittleness is due to domain overfitting, which our new training algorithms suppress and instead encourage domain-general hypotheses. While we improve robustness over standard training methods for certain problem settings, performance of ML systems can still vary drastically with domain shifts. It is crucial for developers and stakeholders to understand model vulnerabilities and operational ranges of input, which could be assessed on the fly during the deployment, albeit at a great cost. Instead, we advocate for proactively estimating accuracy surfaces over any combination of prespecified and interpretable domain shifts for performance forecasting. We present a label-efficient estimation to address estimation over a combinatorial space of domain shifts. Further, when a model's performance on a target domain is found to be poor, traditional approaches adapt the model using the target domain's resources. Standard adaptation methods assume access to sufficient labeled resources, which may be impractical for deployed models. We initiate a study of lightweight adaptation techniques with only unlabeled data resources with a focus on language applications.

Silent speech interface is a promising technology that enables private communications in natural language. However, previous approaches only support a small and inflexible vocabulary, which leads to limited expressiveness. We leverage contrastive learning to learn efficient lipreading representations, enabling few-shot command customization with minimal user effort. Our model exhibits high robustness to different lighting, posture, and gesture conditions on an in-the-wild dataset. For 25-command classification, an F1-score of 0.8947 is achievable only using one shot, and its performance can be further boosted by adaptively learning from more data. This generalizability allowed us to develop a mobile silent speech interface empowered with on-device fine-tuning and visual keyword spotting. A user study demonstrated that with LipLearner, users could define their own commands with high reliability guaranteed by an online incremental learning scheme. Subjective feedback indicated that our system provides essential functionalities for customizable silent speech interactions with high usability and learnability.