There has been a growing interest in model-agnostic methods that can make deep learning models more transparent and explainable to a user. Some researchers recently argued that for a machine to achieve a certain degree of human-level explainability, this machine needs to provide human causally understandable explanations, also known as causability. A specific class of algorithms that have the potential to provide causability are counterfactuals. This paper presents an in-depth systematic review of the diverse existing body of literature on counterfactuals and causability for explainable artificial intelligence. We performed an LDA topic modelling analysis under a PRISMA framework to find the most relevant literature articles. This analysis resulted in a novel taxonomy that considers the grounding theories of the surveyed algorithms, together with their underlying properties and applications in real-world data. This research suggests that current model-agnostic counterfactual algorithms for explainable AI are not grounded on a causal theoretical formalism and, consequently, cannot promote causability to a human decision-maker. Our findings suggest that the explanations derived from major algorithms in the literature provide spurious correlations rather than cause/effects relationships, leading to sub-optimal, erroneous or even biased explanations. This paper also advances the literature with new directions and challenges on promoting causability in model-agnostic approaches for explainable artificial intelligence.

We introduce the task of changing the narrative point of view, where characters are assigned a narrative perspective that is different from the one originally used by the writer. The resulting shift in the narrative point of view alters the reading experience and can be used as a tool in fiction writing or to generate types of text ranging from educational to self-help and self-diagnosis. We introduce a benchmark dataset containing a wide range of types of narratives annotated with changes in point of view from deictic (first or second person) to anaphoric (third person) and describe a pipeline for processing raw text that relies on a neural architecture for mention selection. Evaluations on the new benchmark dataset show that the proposed architecture substantially outperforms the baselines by generating mentions that are less ambiguous and more natural.

Recently, significant advancements have been made in face recognition technologies using Deep Neural Networks. As a result, companies such as Microsoft, Amazon, and Naver offer highly accurate commercial face recognition web services for diverse applications to meet the end-user needs. Naturally, however, such technologies are threatened persistently, as virtually any individual can quickly implement impersonation attacks. In particular, these attacks can be a significant threat for authentication and identification services, which heavily rely on their underlying face recognition technologies' accuracy and robustness. Despite its gravity, the issue regarding deepfake abuse using commercial web APIs and their robustness has not yet been thoroughly investigated. This work provides a measurement study on the robustness of black-box commercial face recognition APIs against Deepfake Impersonation (DI) attacks using celebrity recognition APIs as an example case study. We use five deepfake datasets, two of which are created by us and planned to be released. More specifically, we measure attack performance based on two scenarios (targeted and non-targeted) and further analyze the differing system behaviors using fidelity, confidence, and similarity metrics. Accordingly, we demonstrate how vulnerable face recognition technologies from popular companies are to DI attack, achieving maximum success rates of 78.0% and 99.9% for targeted (i.e., precise match) and non-targeted (i.e., match with any celebrity) attacks, respectively. Moreover, we propose practical defense strategies to mitigate DI attacks, reducing the attack success rates to as low as 0% and 0.02% for targeted and non-targeted attacks, respectively.

OBJECTIVES: Childhood blindness from retinopathy of prematurity (ROP) is increasing as a result of improvements in neonatal care worldwide. We evaluate the effectiveness of artificial intelligence (AI)-based screening in an Indian ROP telemedicine program and whether differences in ROP severity between neonatal care units (NCUs) identified by using AI are related to differences in oxygen-titrating capability. All images were assigned an ROP severity score (1-9) by using the Imaging and Informatics in Retinopathy of Prematurity Deep Learning system. We calculated the area under the receiver operating characteristic curve and sensitivity and specificity for treatment-requiring retinopathy of prematurity. Using multivariable linear regression, we evaluated the mean and median ROP severity in each NCU as a function of mean birth weight, gestational age, and the presence of oxygen blenders and pulse oxygenation monitors.

Explainable NLP (ExNLP) has increasingly focused on collecting human-annotated explanations. These explanations are used downstream in three ways: as data augmentation to improve performance on a predictive task, as a loss signal to train models to produce explanations for their predictions, and as a means to evaluate the quality of model-generated explanations. In this review, we identify three predominant classes of explanations (highlights, free-text, and structured), organize the literature on annotating each type, point to what has been learned to date, and give recommendations for collecting ExNLP datasets in the future.

On a recent afternoon, Mr. Luckey, dressed as if ready for the beach in a Hawaiian-like shirt, shorts and flip-flops, joined other Anduril employees at the company's testing site near Camp Pendleton, a Marine training facility. As the drone took off and swooped between the hills, Mr. Luckey said it could track an object and capture detailed images from seven football fields away. Using many of the artificial intelligence technologies that underpin self-driving cars, Anduril's drones can identify and track vehicles, people and other objects largely on their own. The drones are not armed, but could be useful for guarding bases or reconnaissance. The same sensor technologies that allow the drones to fly on their own could also be used to identify targets on a battlefield.

Machine learners, deep learning practitioners, and data scientists are continually looking for the edge on their performance-oriented devices. That's why we looked at over 2,000 laptops to bring you what we consider the best laptops for your projects on machine learning, deep learning, and data science. We will continuously update this resource with powerful and more performant laptops for every budget as technology continues to evolve to bring you the best suggestions for your machine learning, data science, and deep learning projects and adventures. Our mailbox is full of emails from AI enthusiasts asking us for the best laptops for AI projects. That's why we decided to make this list.

Prediction tasks related to congestion are targeted at improving the level of service of the transportation network. With increasing access to larger datasets of higher resolution, the relevance of deep learning in such prediction tasks, is increasing. Several comprehensive survey papers in recent years have summarised the deep learning applications in the transportation domain. However, the system dynamics of the transportation network vary greatly between the non-congested state and the congested state -- thereby necessitating the need for a clear understanding of the challenges specific to congestion prediction. In this survey, we present the current state of deep learning applications in the tasks related to detection, prediction and propagation of congestion. Recurrent and non-recurrent congestion are discussed separately. Our survey leads us to uncover inherent challenges and gaps in the current state of research. Finally, we present some suggestions for future research directions as answers to the identified challenges.

Swift for TensorFlow, a Google-led project to integrate the TensorFlow machine learning library and Apple's Swift language, is no longer in active development. Nevertheless, parts of the effort live on, including language-differentiated programming for Swift. The GitHub repo for the project notes it is now in archive mode and will not receive further updates. The project, the repo notes, was positioned as a new way to develop machine learning models. "Swift for TensorFlow was an experiment in the next-generation platform for machine learning, incorporating the latest research across machine learning, compilers, differentiable programming, systems design, and beyond."

Increasing automation in the healthcare sector calls for a Hybrid Intelligence (HI) approach to closely study and design the collaboration of humans and autonomous machines. Ensuring that medical HI systems' decision-making is ethical is key. The use of Team Design Patterns (TDPs) can advance this goal by describing successful and reusable configurations of design problems in which decisions have a moral component, as well as through facilitating communication in multidisciplinary teams designing HI systems. For this research, TDPs were developed to describe a set of solutions for two design problems in a medical HI system: (1) mitigating harmful biases in machine learning algorithms and (2) sharing health and behavioral patient data with healthcare professionals and system developers. The Socio-Cognitive Engineering methodology was employed, integrating operational demands, human factors knowledge, and a technological analysis into a set of TDPs. A survey was created to assess the usability of the patterns on their understandability, effectiveness, and generalizability. The results showed that TDPs are a useful method to unambiguously describe solutions for diverse HI design problems with a moral component on varying abstraction levels, that are usable by a heterogeneous group of multidisciplinary researchers. Additionally, results indicated that the SCE approach and the developed questionnaire are suitable methods for creating and assessing TDPs. The study concludes with a set of proposed improvements to TDPs, including their integration with Interaction Design Patterns, the inclusion of several additional concepts, and a number of methodological improvements. Finally, the thesis recommends directions for future research.