This paper compares the performances of three supervised machine learning algorithms in terms of predictive ability and model interpretation on structured or tabular data. The algorithms considered were scikit-learn implementations of extreme gradient boosting machines (XGB) and random forests (RFs), and feedforward neural networks (FFNNs) from TensorFlow. The paper is organized in a findings-based manner, with each section providing general conclusions supported by empirical results from simulation studies that cover a wide range of model complexity and correlation structures among predictors. We considered both continuous and binary responses of different sample sizes. Overall, XGB and FFNNs were competitive, with FFNNs showing better performance in smooth models and tree-based boosting algorithms performing better in non-smooth models. This conclusion held generally for predictive performance, identification of important variables, and determining correct input-output relationships as measured by partial dependence plots (PDPs). FFNNs generally had less over-fitting, as measured by the difference in performance between training and testing datasets. However, the difference with XGB was often small. RFs did not perform well in general, confirming the findings in the literature. All models exhibited different degrees of bias seen in PDPs, but the bias was especially problematic for RFs. The extent of the biases varied with correlation among predictors, response type, and data set sample size. In general, tree-based models tended to over-regularize the fitted model in the tails of predictor distributions. Finally, as to be expected, performances were better for continuous responses compared to binary data and with larger samples.

It is no longer enough to build models that make accurate predictions. We also need to make sure that those predictions are fair. Doing so will reduce the harm of biased predictions. As a result, you will go a long way in building trust in your AI systems. To correct bias we need to start by analysing fairness in data and models. You can see a summary of the approaches we will cover below. Understanding why a model is unfair is more complicated. This is why we will first do an exploratory fairness analysis. This will help you identify potential sources of bias before you start modelling. We will then move on to measuring fairness. This is done by applying different definitions of fairness. We will discuss the theory behind these approaches. Along the way, we will also be applying them using Python. We will discuss key pieces of code and you can find the full project on GitHub. You should still be able to follow the article even if you do not want to use the Python code.

In this contribution, we investigate the effectiveness of deep fusion of text and audio features for categorical and dimensional speech emotion recognition (SER). We propose a novel, multistage fusion method where the two information streams are integrated in several layers of a deep neural network (DNN), and contrast it with a single-stage one where the streams are merged in a single point. Both methods depend on extracting summary linguistic embeddings from a pre-trained BERT model, and conditioning one or more intermediate representations of a convolutional model operating on log-Mel spectrograms. Experiments on the MSP-Podcast and IEMOCAP datasets demonstrate that the two fusion methods clearly outperform a shallow (late) fusion baseline and their unimodal constituents, both in terms of quantitative performance and qualitative behaviour. Overall, our multistage fusion shows better quantitative performance, surpassing alternatives on most of our evaluations. This illustrates the potential of multistage fusion in better assimilating text and audio information.

Editor's Note: It has come to our attention that several statements in this article have been based on sources that have later been recanted and are factually incorrect. Court documents from the case show that ShotSpotter accurately showed the location of the gunfire as reported in both the real-time alert, as well as in the forensic report. The initial alert was classified as a possible firework, but through their standard procedure of human analysis, it was determined within one minute to be gunfire. The evidence that ShotSpotter provided was later withdrawn by the prosecution and had no bearing on the results of the case. Sixty-five-year-old Michael Williams was released from jail last month after spending almost a year in jail on a murder charge.

One of the first steps in many text-based social science studies is to retrieve documents that are relevant for the analysis from large corpora of otherwise irrelevant documents. The conventional approach in social science to address this retrieval task is to apply a set of keywords and to consider those documents to be relevant that contain at least one of the keywords. But the application of incomplete keyword lists risks drawing biased inferences. More complex and costly methods such as query expansion techniques, topic model-based classification rules, and active as well as passive supervised learning could have the potential to more accurately separate relevant from irrelevant documents and thereby reduce the potential size of bias. Yet, whether applying these more expensive approaches increases retrieval performance compared to keyword lists at all, and if so, by how much, is unclear as a comparison of these approaches is lacking. This study closes this gap by comparing these methods across three retrieval tasks associated with a data set of German tweets (Linder, 2017), the Social Bias Inference Corpus (SBIC) (Sap et al., 2020), and the Reuters-21578 corpus (Lewis, 1997). Results show that query expansion techniques and topic model-based classification rules in most studied settings tend to decrease rather than increase retrieval performance. Active supervised learning, however, if applied on a not too small set of labeled training instances (e.g.

In this paper we describe an approach for anomaly detection and its explainability in multivariate functional data. The anomaly detection procedure consists of transforming the series into a vector of features and using an Isolation forest algorithm. The explainable procedure is based on the computation of the SHAP coefficients and on the use of a supervised decision tree. We apply it on simulated data to measure the performance of our method and on real data coming from industry.

Advances in machine learning methods provide tools that have broad applicability in scientific research. These techniques are being applied across the diversity of nuclear physics research topics, leading to advances that will facilitate scientific discoveries and societal applications. This Review gives a snapshot of nuclear physics research which has been transformed by machine learning techniques.

For patients suffering from brain tumor, prognosis estimation and treatment decisions are made by a multidisciplinary team based on a set of preoperative MR scans. Currently, the lack of standardized and automatic methods for tumor detection and generation of clinical reports represents a major hurdle. In this study, we investigate glioblastomas, lower grade gliomas, meningiomas, and metastases, through four cohorts of up to 4000 patients. Tumor segmentation models were trained using the AGU-Net architecture with different preprocessing steps and protocols. Segmentation performances were assessed in-depth using a wide-range of voxel and patient-wise metrics covering volume, distance, and probabilistic aspects. Finally, two software solutions have been developed, enabling an easy use of the trained models and standardized generation of clinical reports: Raidionics and Raidionics-Slicer. Segmentation performances were quite homogeneous across the four different brain tumor types, with an average true positive Dice ranging between 80% and 90%, patient-wise recall between 88% and 98%, and patient-wise precision around 95%. With our Raidionics software, running on a desktop computer with CPU support, tumor segmentation can be performed in 16 to 54 seconds depending on the dimensions of the MRI volume. For the generation of a standardized clinical report, including the tumor segmentation and features computation, 5 to 15 minutes are necessary. All trained models have been made open-access together with the source code for both software solutions and validation metrics computation. In the future, an automatic classification of the brain tumor type would be necessary to replace manual user input. Finally, the inclusion of post-operative segmentation in both software solutions will be key for generating complete post-operative standardized clinical reports.

Early detection of lung nodules with computed tomography (CT) is critical for the longer survival of lung cancer patients and better quality of life. Computer-aided detection/diagnosis (CAD) is proven valuable as a second or concurrent reader in this context. However, accurate detection of lung nodules remains a challenge for such CAD systems and even radiologists due to not only the variability in size, location, and appearance of lung nodules but also the complexity of lung structures. This leads to a high false-positive rate with CAD, compromising its clinical efficacy. Motivated by recent computer vision techniques, here we present a self-supervised region-based 3D transformer model to identify lung nodules among a set of candidate regions. Specifically, a 3D vision transformer (ViT) is developed that divides a CT image volume into a sequence of non-overlap cubes, extracts embedding features from each cube with an embedding layer, and analyzes all embedding features with a self-attention mechanism for the prediction. To effectively train the transformer model on a relatively small dataset, the region-based contrastive learning method is used to boost the performance by pre-training the 3D transformer with public CT images. Our experiments show that the proposed method can significantly improve the performance of lung nodule screening in comparison with the commonly used 3D convolutional neural networks.

Due to the unspecified and dynamic nature of data streams, online machine learning requires powerful and flexible solutions. However, evaluating online machine learning methods under realistic conditions is difficult. Existing work therefore often draws on different heuristics and simulations that do not necessarily produce meaningful and reliable results. Indeed, in the absence of common evaluation standards, it often remains unclear how online learning methods will perform in practice or in comparison to similar work. In this paper, we propose a comprehensive set of properties for high-quality machine learning in evolving data streams. In particular, we discuss sensible performance measures and evaluation strategies for online predictive modelling, online feature selection and concept drift detection. As one of the first works, we also look at the interpretability of online learning methods. The proposed evaluation standards are provided in a new Python framework called float. Float is completely modular and allows the simultaneous integration of common libraries, such as scikit-multiflow or river, with custom code. Float is open-sourced and can be accessed at https://github.com/haugjo/float. In this sense, we hope that our work will contribute to more standardized, reliable and realistic testing and comparison of online machine learning methods.