Machine learning systems are becoming increasingly ubiquitous. These systems’s adoption has been expanding, accelerating the shift towards a more algorithmic society, meaning that algorithmically informed decisions have greater potential for significant social impact. However, most of these accurate decision support systems remain complex black boxes, meaning their internal logic and inner workings are hidden to the user and even experts cannot fully understand the rationale behind their predictions. Moreover, new regulations and highly regulated domains have made the audit and verifiability of decisions mandatory, increasing the demand for the ability to question, understand, and trust machine learning systems, for which interpretability is indispensable. The research community has recognized this interpretability problem and focused on developing both interpretable models and explanation methods over the past few years. However, the emergence of these methods shows there is no consensus on how to assess the explanation quality. Which are the most suitable metrics to assess the quality of an explanation? The aim of this article is to provide a review of the current state of the research field on machine learning interpretability while focusing on the societal impact and on the developed methods and metrics. Furthermore, a complete literature review is presented in order to identify future directions of work on this field.

Mammography screening is one of the most widely deployed tools for early breast cancer detection and has been shown to decrease mortality in multiple randomized clinical trials.¹ However, screening mammography is imperfect with 1 in 8 cancers missed at time of interpretation in US community practice.² Roughly 9% to 10% of the 40 million US women who undergo routine breast screening each year are recalled for additional diagnostic imaging; only 4% to 5% of women recalled are ultimately diagnosed as having breast cancer.² These false positives lead to preventable harms, included patient anxiety, benign biopsies, and unnecessary intervention or treatment.³ High false-positive rates incur significant resources and contribute to the annual $10 billion mammography screening costs in the United States.⁴

Using recent results from numerical relativity simulations of nonspinning binary black hole mergers, we revisit the problem of detecting ringdown waveforms and of estimating the source parameters, considering both LISA and Earth-based interferometers. We find that Advanced LIGO and EGO could detect intermediate-mass black holes of mass up to $\sim {10}^3{M}_{\odot }$ out to a luminosity distance of a few Gpc. For typical multipolar energy distributions, we show that the single-mode ringdown templates presently used for ringdown searches in the LIGO data stream can produce a significant event loss ($>10\%$ for all detectors in a large interval of black hole masses) and very large parameter estimation errors on the black hole’s mass and spin. We estimate that more than $\sim {10}^6$ templates would be needed for a single-stage multimode search. Therefore, we recommend a “two-stage” search to save on computational costs: single-mode templates can be used for detection, but multimode templates or Prony methods should be used to estimate parameters once a detection has been made. We update estimates of the critical signal-to-noise ratio required to test the hypothesis that two or more modes are present in the signal and to resolve their frequencies, showing that second-generation Earth-based detectors and LISA have the potential to perform no-hair tests.

The field of Deep Learning (DL) has seen a remarkable series of developments with increasingly accurate and robust algorithms. However, the increase in performance has been accompanied by an increase in the parameters, complexity, and training and inference time of the models, which means that we are rapidly reaching a point where DL may no longer be feasible. On the other hand, some specific applications need to be carefully considered when developing DL models due to hardware limitations or power requirements. In this context, there is a growing interest in efficient DL algorithms, with Spiking Neural Networks (SNNs) being one of the most promising paradigms. Due to the inherent asynchrony and sparseness of spike trains, these types of networks have the potential to reduce power consumption while maintaining relatively good performance. This is attractive for efficient DL and, if successful, could replace traditional Artificial Neural Networks (ANNs) in many applications. However, despite significant progress, the performance of SNNs on benchmark datasets is often lower than that of traditional ANNs. Moreover, due to the non-differentiable nature of their activation functions, it is difficult to train SNNs with direct backpropagation, so appropriate training strategies must be found. Nevertheless, significant efforts have been made to develop competitive models. This survey covers the main ideas behind SNNs and reviews recent trends in learning rules and network architectures, with a particular focus on biologically inspired strategies. It also provides some practical considerations of state-of-the-art SNNs and discusses relevant research opportunities.

For centuries, music has been shared and remembered by two traditions: aural transmission and in the form of written documents normally called musical scores. Many of these scores exist in the form of unpublished manuscripts and hence they are in danger of being lost through the normal ravages of time. To preserve the music some form of typesetting or, ideally, a computer system that can automatically decode the symbolic images and create new scores is required. Programs analogous to optical character recognition systems called optical music recognition (OMR) systems have been under intensive development for many years. However, the results to date are far from ideal. Each of the proposed methods emphasizes different properties and therefore makes it difficult to effectively evaluate its competitive advantages. This article provides an overview of the literature concerning the automatic analysis of images of printed and handwritten musical scores. For self-containment and for the benefit of the reader, an introduction to OMR processing systems precedes the literature overview. The following study presents a reference scheme for any researcher wanting to compare new OMR algorithms against well-known ones.