Bias detection in data and model outcomes is a fundamental requirement for building responsible artificial intelligence (AI) and machine learning (ML) models. Unfortunately, detecting bias isn't an easy task for the vast majority of practitioners due to the large number of ways in which it can be measured and different factors that can contribute to a biased outcome. For instance, an imbalanced sampling of the training data may result in a model that is less accurate for certain subsets of the data. Bias may also be introduced by the ML algorithm itself--even with a well-balanced training dataset, the outcomes might favor certain subsets of the data as compared to the others. To detect bias, you must have a thorough understanding of different types of bias and the corresponding bias metrics. For example, at the time of this writing, Amazon SageMaker Clarify offers 21 different metrics to choose from.

Ensembling neural networks is a long-standing technique for improving the generalization error of neural networks by combining networks with orthogonal properties via a committee decision. We show that this technique is an ideal fit for machine learning on medical data: First, ensembles are amenable to parallel and asynchronous learning, thus enabling efficient training of patient-specific component neural networks. Second, building on the idea of minimizing generalization error by selecting uncorrelated patient-specific networks, we show that one can build an ensemble of a few selected patient-specific models that outperforms a single model trained on much larger pooled datasets. Third, the non-iterative ensemble combination step is an optimal low-dimensional entry point to apply output perturbation to guarantee the privacy of the patient-specific networks. We exemplify our framework of differentially private ensembles on the task of early prediction of sepsis, using real-life intensive care unit data labeled by clinical experts.

Machine Learning (ML) is a predominant tool nowadays to solve several challenges in different industries, such as credit scoring Provenzano et al. [2020], fraud analysis Tiwari et al. [2021], product recommendation Rohde et al. [2018], and demand forecasting Masini et al. [2020], among other extensively explored use cases. Under this premise, the research of the quantum computing properties applied to ML has expanded rapidly in recent years since a proven advantage could be a highly useful cross-industry. The recent progress of these explorations in Quantum Machine Learning (QML) Mishra et al. [2021] put a spotlight on quantum technology, introducing a challenge to determine if QML will provide an advantage over classical machine learning or not. The actual devices are noisy, meaning that the depth or consecutive gate operations are limited [Ristè et al., 2013, Burnett et al., 2019, Wang et al., 2021]. Qubits will lose their entanglement and so, the information. These devices make up the NISQ era Preskill [2018] and limit the use of quantum algorithms or hybrid algorithms to be useful Callison and Chancellor [2022].

Understanding the long-term evolution of hierarchical triple systems is challenging due to its inherent chaotic nature, and it requires computationally expensive simulations. Here we propose a convolutional neural network model to predict the stability of hierarchical triples by looking at their evolution during the first $5 \times 10^5$ inner binary orbits. We employ the regularized few-body code TSUNAMI to simulate $5\times 10^6$ hierarchical triples, from which we generate a large training and test dataset. We develop twelve different network configurations that use different combinations of the triples' orbital elements and compare their performances. Our best model uses 6 time-series, namely, the semimajor axes ratio, the inner and outer eccentricities, the mutual inclination and the arguments of pericenter. This model achieves an area under the curve of over $95\%$ and informs of the relevant parameters to study triple systems stability. All trained models are made publicly available, allowing to predict the stability of hierarchical triple systems $200$ times faster than pure $N$-body methods.

Texture-based studies and designs have been in focus recently. Whisker-based multidimensional surface texture data is missing in the literature. This data is critical for robotics and machine perception algorithms in the classification and regression of textural surfaces. In this study, we present a novel sensor design to acquire multidimensional texture information. The surface texture's roughness and hardness were measured experimentally using sweeping and dabbing. Three machine learning models (SVM, RF, and MLP) showed excellent classification accuracy for the roughness and hardness of surface textures. We show that the combination of pressure and accelerometer data, collected from a standard machined specimen using the whisker sensor, improves classification accuracy. Further, we experimentally validate that the sensor can classify texture with roughness depths as low as $2.5\mu m$ at an accuracy of $90\%$ or more and segregate materials based on their roughness and hardness. We present a novel metric to consider while designing a whisker sensor to guarantee the quality of texture data acquisition beforehand. The machine learning model performance was validated against the data collected from the laser sensor from the same set of surface textures. As part of our work, we are releasing two-dimensional texture data: roughness and hardness to the research community.

As structured data are often insufficient, labels need to be extracted from free text in electronic health records when developing models for clinical information retrieval and decision support systems. One of the most important contextual properties in clinical text is negation, which indicates the absence of findings. We aimed to improve large scale extraction of labels by comparing three methods for negation detection in Dutch clinical notes. We used the Erasmus Medical Center Dutch Clinical Corpus to compare a rule-based method based on ContextD, a biLSTM model using MedCAT and (finetuned) RoBERTa-based models. We found that both the biLSTM and RoBERTa models consistently outperform the rule-based model in terms of F1 score, precision and recall. In addition, we systematically categorized the classification errors for each model, which can be used to further improve model performance in particular applications. Combining the three models naively was not beneficial in terms of performance. We conclude that the biLSTM and RoBERTa-based models in particular are highly accurate accurate in detecting clinical negations, but that ultimately all three approaches can be viable depending on the use case at hand.

Typo-squatting domains are a common cyber-attack technique. It involves utilising domain names, that exploit possible typographical errors of commonly visited domains, to carry out malicious activities such as phishing, malware installation, etc. Current approaches typically revolve around string comparison algorithms like the Demaru-Levenschtein Distance (DLD) algorithm. Such techniques do not take into account keyboard distance, which researchers find to have a strong correlation with typical typographical errors and are trying to take account of. In this paper, we present the TypoSwype framework which converts strings to images that take into account keyboard location innately. We also show how modern state of the art image recognition techniques involving Convolutional Neural Networks, trained via either Triplet Loss or NT-Xent Loss, can be applied to learn a mapping to a lower dimensional space where distances correspond to image, and equivalently, textual similarity. Finally, we also demonstrate our method's ability to improve typo-squatting detection over the widely used DLD algorithm, while maintaining the classification accuracy as to which domain the input domain was attempting to typo-squat.

Action recognition from videos, i.e., classifying a video into one of the pre-defined action types, has been a popular topic in the communities of artificial intelligence, multimedia, and signal processing. However, existing methods usually consider an input video as a whole and learn models, e.g., Convolutional Neural Networks (CNNs), with coarse video-level class labels. These methods can only output an action class for the video, but cannot provide fine-grained and explainable cues to answer why the video shows a specific action. Therefore, researchers start to focus on a new task, Part-level Action Parsing (PAP), which aims to not only predict the video-level action but also recognize the frame-level fine-grained actions or interactions of body parts for each person in the video. To this end, we propose a coarse-to-fine framework for this challenging task. In particular, our framework first predicts the video-level class of the input video, then localizes the body parts and predicts the part-level action. Moreover, to balance the accuracy and computation in part-level action parsing, we propose to recognize the part-level actions by segment-level features. Furthermore, to overcome the ambiguity of body parts, we propose a pose-guided positional embedding method to accurately localize body parts. Through comprehensive experiments on a large-scale dataset, i.e., Kinetics-TPS, our framework achieves state-of-the-art performance and outperforms existing methods over a 31.10% ROC score.

Today, data collection has improved in various areas, and the medical domain is no exception. Auscultation, as an important diagnostic technique for physicians, due to the progress and availability of digital stethoscopes, lends itself well to applications of machine learning. Due to the large number of auscultations performed, the availability of data opens up an opportunity for more effective analysis of sounds where prognostic accuracy even among experts remains low. In this study, digital 6-channel auscultations of 45 patients were used in various machine learning scenarios, with the aim of distinguishing between normal and anomalous pulmonary sounds. Audio features (such as fundamental frequencies F0-4, loudness, HNR, DFA, as well as descriptive statistics of log energy, RMS and MFCC) were extracted using the Python library Surfboard. Windowing and feature aggregation and concatenation strategies were used to prepare data for tree-based ensemble models in unsupervised (fair-cut forest) and supervised (random forest) machine learning settings. The evaluation was carried out using 9-fold stratified cross-validation repeated 30 times. Decision fusion by averaging outputs for a subject was tested and found to be useful. Supervised models showed a consistent advantage over unsupervised ones, achieving mean AUC ROC of 0.691 (accuracy 71.11%, Kappa 0.416, F1-score 0.771) in side-based detection and mean AUC ROC of 0.721 (accuracy 68.89%, Kappa 0.371, F1-score 0.650) in patient-based detection.

In recent years, the number of machine learning (ML) technologies gaining regulatory approval for healthcare has increased significantly allowing them to be placed on the market. However, the regulatory frameworks applied to them were originally devised for traditional software, which has largely rule-based behaviour, compared to the data-driven and learnt behaviour of ML. As the frameworks are in the process of reformation, there is a need to proactively assure the safety of ML to prevent patient safety being compromised. The Assurance of Machine Learning for use in Autonomous Systems (AMLAS) methodology was developed by the Assuring Autonomy International Programme based on well-established concepts in system safety. This review has appraised the methodology by consulting ML manufacturers to understand if it converges or diverges from their current safety assurance practices, whether there are gaps and limitations in its structure and if it is fit for purpose when applied to the healthcare domain. Through this work we offer the view that there is clear utility for AMLAS as a safety assurance methodology when applied to healthcare machine learning technologies, although development of healthcare specific supplementary guidance would benefit those implementing the methodology.