Facial recognition software used by the UK's biggest police force has returned false positives in more than 98 per cent of alerts generated, The Independent can reveal, with the country's biometrics regulator calling it "not yet fit for use". The Metropolitan Police's system has produced 104 alerts of which only two were later confirmed to be positive matches, a freedom of information request showed. In its response the force said it did not consider the inaccurate matches "false positives" because alerts were checked a second time after they occurred. Facial recognition technology scans people in a video feed and compares their images to pictures stored in a reference library or watch list. It has been used at large events like the Notting Hill Carnival and a Six Nations Rugby match. The system used by another force, South Wales Police, has returned more than 2,400 false positives in 15 deployments since June 2017.

In the era of "big data", it is becoming more of a challenge to not only build state-of-the-art predictive models, but also gain an understanding of what's really going on in the data. For example, it is often of interest to know which, if any, of the predictors in a fitted model are relatively influential on the predicted outcome. Some modern algorithms---like random forests and gradient boosted decision trees---have a natural way of quantifying the importance or relative influence of each feature. Other algorithms---like naive Bayes classifiers and support vector machines---are not capable of doing so and model-free approaches are generally used to measure each predictor's importance. In this paper, we propose a standardized, model-based approach to measuring predictor importance across the growing spectrum of supervised learning algorithms. Our proposed method is illustrated through both simulated and real data examples. The R code to reproduce all of the figures in this paper is available in the supplementary materials.

Ensemble learning is a powerful approach to construct a strong learner from multiple base learners. The most popular way to aggregate an ensemble of classifiers is majority voting, which assigns a sample to the class that most base classifiers vote for. However, improved performance can be obtained by assigning weights to the base classifiers according to their accuracy. This paper proposes an agreement rate initialized maximum likelihood estimator (ARIMLE) to optimally fuse the base classifiers. ARIMLE first uses a simplified agreement rate method to estimate the classification accuracy of each base classifier from the unlabeled samples, then employs the accuracies to initialize a maximum likelihood estimator (MLE), and finally uses the expectation-maximization algorithm to refine the MLE. Extensive experiments on visually evoked potential classification in a brain-computer interface application show that ARIMLE outperforms majority voting, and also achieves better or comparable performance with several other state-of-the-art classifier combination approaches.

Acute kidney injury (AKI) is a common and serious complication after a surgery which is associated with morbidity and mortality. The majority of existing perioperative AKI risk score prediction models are limited in their generalizability and do not fully utilize the physiological intraoperative time-series data. Thus, there is a need for intelligent, accurate, and robust systems, able to leverage information from large-scale data to predict patient's risk of developing postoperative AKI. A retrospective single-center cohort of 2,911 adult patients who underwent surgery at the University of Florida Health has been used for this study. We used machine learning and statistical analysis techniques to develop perioperative models to predict the risk of AKI (risk during the first 3 days, 7 days, and until the discharge day) before and after the surgery. In particular, we examined the improvement in risk prediction by incorporating three intraoperative physiologic time series data, i.e., mean arterial blood pressure, minimum alveolar concentration, and heart rate. For an individual patient, the preoperative model produces a probabilistic AKI risk score, which will be enriched by integrating intraoperative statistical features through a machine learning stacking approach inside a random forest classifier. We compared the performance of our model based on the area under the receiver operating characteristics curve (AUROC), accuracy and net reclassification improvement (NRI). The predictive performance of the proposed model is better than the preoperative data only model. For AKI-7day outcome: The AUC was 0.86 (accuracy was 0.78) in the proposed model, while the preoperative AUC was 0.84 (accuracy 0.76). Furthermore, with the integration of intraoperative features, we were able to classify patients who were misclassified in the preoperative model.

Machine learning methods have gained a great deal of popularity in recent years among public administration scholars and practitioners. These techniques open the door to the analysis of text, image and other types of data that allow us to test foundational theories of public administration and to develop new theories. Despite the excitement surrounding machine learning methods, clarity regarding their proper use and potential pitfalls is lacking. This paper attempts to fill this gap in the literature through providing a machine learning "guide to practice" for public administration scholars and practitioners. Here, we take a foundational view of machine learning and describe how these methods can enrich public administration research and practice through their ability develop new measures, tap into new sources of data and conduct statistical inference and causal inference in a principled manner. We then turn our attention to the pitfalls of using these methods such as unvalidated measures and lack of interpretability. Finally, we demonstrate how machine learning techniques can help us learn about organizational reputation in federal agencies through an illustrated example using tweets from 13 executive federal agencies.

Cellular Electron CryoTomography (CECT) is a 3D imaging technique that captures information about the structure and spatial organization of macromolecular complexes within single cells, in near-native state and at sub-molecular resolution. Although template matching is often used to locate macromolecules in a CECT image, it is insufficient as it only measures the relative structural similarity. Therefore, it is preferable to assess the statistical credibility of the decision through hypothesis testing, requiring many templates derived from a diverse population of macromolecular structures. Due to the very limited number of known structures, we need a generative model to efficiently and reliably sample pseudo-structures from the complex distribution of macromolecular structures. To address this challenge, we propose a novel image-derived approach for performing hypothesis testing for template matching by constructing generative models using the generative adversarial network. Finally, we conducted hypothesis testing experiments for template matching on both simulated and experimental subtomograms, allowing us to conclude the identity of subtomograms with high statistical credibility and significantly reducing false positives.

Last week was a busy one for the conversation around digital privacy as Facebook fired an employee of its security division for allegedly misusing his privileged access to stalk women, while the Wall Street Journal broke the story that the company's own employees are protected by a special privacy feature that alerts them when its security employees access their profiles. In the space of just one week, it emerged that Facebook's security staff can access any of the platform's ordinary two billion profiles and rummage through them without the user ever knowing their information has been accessed, while if those same security staff attempt to access a fellow Facebook employee's profile to investigate misconduct or illegal activity, that employee will receive a notice they are being investigated. What does this double standard teach us about how social media platforms view their users? Perhaps the most interesting element of Facebook's system, originally called "Sauron alert" and now known simply as "Security Watchdog" is that alerts are sent directly to the employees whose profiles are accessed, rather than to corporate legal, human resources or some other watchdog division. One could imagine a process in which all accesses to employee profiles are routed to a dedicated staff in the legal department to review for appropriateness. Under this model the employee whose profile is accessed by security would never know their profile was viewed.

We introduce a new neural network model, together with a tractable and monotone online learning algorithm. Our model describes feed-forward networks for classification, with one output node for each class. The only nonlinear operation is rectification using a ReLU function with a bias. However, there is a rectifier on every edge rather than at the nodes of the network. There are also weights, but these are positive, static, and associated with the nodes. Our "rectified wire" networks are able to represent arbitrary Boolean functions. Only the bias parameters, on the edges of the network, are learned. Another departure in our approach, from standard neural networks, is that the loss function is replaced by a constraint. This constraint is simply that the value of the output node associated with the correct class should be zero. Our model has the property that the exact norm-minimizing parameter update, required to correctly classify a training item, is the solution to a quadratic program that can be computed with a few passes through the network. We demonstrate a training algorithm using this update, called sequential deactivation (SDA), on MNIST and some synthetic datasets. Upon adopting a natural choice for the nodal weights, SDA has no hyperparameters other than those describing the network structure. Our experiments explore behavior with respect to network size and depth in a family of sparse expander networks.

Current approaches in approximate inference for Bayesian neural networks minimise the Kullback-Leibler divergence to approximate the true posterior over the weights. However, this approximation is without knowledge of the final application, and therefore cannot guarantee optimal predictions for a given task. To make more suitable task-specific approximations, we introduce a new loss-calibrated evidence lower bound for Bayesian neural networks in the context of supervised learning, informed by Bayesian decision theory. By introducing a lower bound that depends on a utility function, we ensure that our approximation achieves higher utility than traditional methods for applications that have asymmetric utility functions. Furthermore, in using dropout inference, we highlight that our new objective is identical to that of standard dropout neural networks, with an additional utility-dependent penalty term. We demonstrate our new loss-calibrated model with an illustrative medical example and a restricted model capacity experiment, and highlight failure modes of the comparable weighted cross entropy approach. Lastly, we demonstrate the scalability of our method to real world applications with per-pixel semantic segmentation on an autonomous driving data set.

In this paper, we propose a novel approach based on cost-sensitive ensemble weighted extreme learning machine; we call this approach AE1-WELM. We apply this approach to text classification. AE1-WELM is an algorithm including balanced and imbalanced multiclassification for text classification. Weighted ELM assigning the different weights to the different samples improves the classification accuracy to a certain extent, but weighted ELM considers the differences between samples in the different categories only and ignores the differences between samples within the same categories. We measure the importance of the documents by the sample information entropy, and generate cost-sensitive matrix and factor based on the document importance, then embed the cost-sensitive weighted ELM into the AdaBoost.M1 framework seamlessly. Vector space model(VSM) text representation produces the high dimensions and sparse features which increase the burden of ELM. To overcome this problem, we develop a text classification framework combining the word vector and AE1-WELM. The experimental results show that our method provides an accurate, reliable and effective solution for text classification.