A close-up of a police facial recognition camera used in Cardiff, Wales. Since 2017, police in the UK have been testing live, or real-time, facial recognition in public places to try to identify criminals. The legality of these trials has been widely questioned by privacy and human rights campaigners, who just won a landmark case that could have a lasting impact on how police use the technology in the future. In a ruling Tuesday, the UK Court of Appeal said South Wales Police had been using the technology unlawfully, which amounted to a violation of human rights. In a case brought by civil liberties campaigner Ed Bridges and supported by human rights group Liberty, three senior judges ruled that the South Wales Police had violated Bridges' right to privacy under the European Convention of Human Rights.

Deep reinforcement learning has shown remarkable success in the past few years. Highly complex sequential decision making problems have been solved in tasks such as game playing and robotics. Unfortunately, the sample complexity of most deep reinforcement learning methods is high, precluding their use in some important applications. Model-based reinforcement learning creates an explicit model of the environment dynamics to reduce the need for environment samples. Current deep learning methods use high-capacity networks to solve high-dimensional problems. Unfortunately, high-capacity models typically require many samples, negating the potential benefit of lower sample complexity in model-based methods. A challenge for deep model-based methods is therefore to achieve high predictive power while maintaining low sample complexity. In recent years, many model-based methods have been introduced to address this challenge. In this paper, we survey the contemporary model-based landscape. First we discuss definitions and relations to other fields. We propose a taxonomy based on three approaches: using explicit planning on given transitions, using explicit planning on learned transitions, and end-to-end learning of both planning and transitions. We use these approaches to organize a comprehensive overview of important recent developments such as latent models. We describe methods and benchmarks, and we suggest directions for future work for each of the approaches. Among promising research directions are curriculum learning, uncertainty modeling, and use of latent models for transfer learning.

Semantic clone detection is the process of finding program elements with similar or equal runtime behavior. For example, detecting the semantic equality between the recursive and iterative implementation of the factorial computation. Semantic clone detection is the de facto technical boundary of clone detectors. This boundary was tested over the last years with interesting new approaches. This work contributes a semantic clone detection approach that detects clones with 0% syntactic similarity. We present Semantic Clone Detection via Probabilistic Software Modeling (SCD-PSM) as a stable and precise solution to semantic clone detection. PSM builds a probabilistic model of a program that is capable of evaluating and generating runtime data. SCD-PSM leverages this model and its model elements to finding behaviorally equal model elements. This behavioral equality is then generalized to semantic equality of the original program elements. It uses the likelihood between model elements as a distance metric. Then, it employs the likelihood ratio significance test to decide whether this distance is significant, given a pre-specified and controllable false-positive rate. The output of SCD-PSM are pairs of program elements (i.e., methods), their distance, and a decision whether they are clones or not. SCD-PSM yields excellent results with a Matthews Correlation Coefficient greater 0.9. These results are obtained on classical semantic clone detection problems such as detecting recursive and iterative versions of an algorithm, but also on complex problems used in coding competitions.

Much has been said about the fusion of bio-inspired optimization algorithms and Deep Learning models for several purposes: from the discovery of network topologies and hyper-parametric configurations with improved performance for a given task, to the optimization of the model's parameters as a replacement for gradient-based solvers. Indeed, the literature is rich in proposals showcasing the application of assorted nature-inspired approaches for these tasks. In this work we comprehensively review and critically examine contributions made so far based on three axes, each addressing a fundamental question in this research avenue: a) optimization and taxonomy (Why?), including a historical perspective, definitions of optimization problems in Deep Learning, and a taxonomy associated with an in-depth analysis of the literature, b) critical methodological analysis (How?), which together with two case studies, allows us to address learned lessons and recommendations for good practices following the analysis of the literature, and c) challenges and new directions of research (What can be done, and what for?). In summary, three axes - optimization and taxonomy, critical analysis, and challenges - which outline a complete vision of a merger of two technologies drawing up an exciting future for this area of fusion research.

In order to resist attacks, various methods have been proposed. A category of defense methods improve network's training regime to counter adversarial attacks. The most common method is adversarial training [23, 31] with adversarial examples added to the training data. In [29], a defense method called Min-Max optimization is introduced to augment the training data with first-order attack samples. There are also some model defense methods that target at removing adversarial perturbation by transforming the input images before feeding them to the network [24, 1, 18].

With the emergence of conversational artificial intelligence (AI) agents, it is important to understand the mechanisms that influence users' experiences of these agents. We study a common tool in the designer's toolkit: conceptual metaphors. Metaphors can present an agent as akin to a wry teenager, a toddler, or an experienced butler. How might a choice of metaphor influence our experience of the AI agent? Sampling metaphors along the dimensions of warmth and competence---defined by psychological theories as the primary axes of variation for human social perception---we perform a study (N=260) where we manipulate the metaphor, but not the behavior, of a Wizard-of-Oz conversational agent. Following the experience, participants are surveyed about their intention to use the agent, their desire to cooperate with the agent, and the agent's usability. Contrary to the current tendency of designers to use high competence metaphors to describe AI products, we find that metaphors that signal low competence lead to better evaluations of the agent than metaphors that signal high competence. This effect persists despite both high and low competence agents featuring human-level performance and the wizards being blind to condition. A second study confirms that intention to adopt decreases rapidly as competence projected by the metaphor increases. In a third study, we assess effects of metaphor choices on potential users' desire to try out the system and find that users are drawn to systems that project higher competence and warmth. These results suggest that projecting competence may help attract new users, but those users may discard the agent unless it can quickly correct with a lower competence metaphor. We close with a retrospective analysis that finds similar patterns between metaphors and user attitudes towards past conversational agents such as Xiaoice, Replika, Woebot, Mitsuku, and Tay.

Psychological semantics is the study of how people represent the meanings of words and then build sentence meaning out of those representations. People use language dozens of time a day--to have conversations and give instructions, to read and write, to label objects and teach. A theory of psychological semantics must provide the basis for how people do all those things, choosing which words to use and understanding the words they read or hear. In this article we focus on the mental representation of word meaning. Human language is still the gold standard for a communication system, but artificial intelligence (AI) systems have made important progress in language use. Research on Natural Language Processing (NLP) develops systems that understand language to the degree that computers can carry out useful tasks. As described below, such systems use vast text corpora to learn about words, using neural networks and other statistical models. The recent explosion of research in NLP, driven largely by advances in neural networks (also called deep learning), has resulted in continuously improving performance on various benchmarks that require interpreting words and sentences. Systems are now used in interfaces with customers to make sales or solve problems.

Events are occurrences in specific locations, time, and semantics that nontrivially impact either our society or the nature, such as civil unrest, system failures, and epidemics. It is highly desirable to be able to anticipate the occurrence of such events in advance in order to reduce the potential social upheaval and damage caused. Event prediction, which has traditionally been prohibitively challenging, is now becoming a viable option in the big data era and is thus experiencing rapid growth. There is a large amount of existing work that focuses on addressing the challenges involved, including heterogeneous multi-faceted outputs, complex dependencies, and streaming data feeds. Most existing event prediction methods were initially designed to deal with specific application domains, though the techniques and evaluation procedures utilized are usually generalizable across different domains. However, it is imperative yet difficult to cross-reference the techniques across different domains, given the absence of a comprehensive literature survey for event prediction. This paper aims to provide a systematic and comprehensive survey of the technologies, applications, and evaluations of event prediction in the big data era. First, systematic categorization and summary of existing techniques are presented, which facilitate domain experts' searches for suitable techniques and help model developers consolidate their research at the frontiers. Then, comprehensive categorization and summary of major application domains are provided. Evaluation metrics and procedures are summarized and standardized to unify the understanding of model performance among stakeholders, model developers, and domain experts in various application domains. Finally, open problems and future directions for this promising and important domain are elucidated and discussed.

Unless you've been holidaying on Mars, or perhaps in Spain (alongside the transport secretary), you may have noticed some fuss on social media about something called GPT-3. The GPT bit stands for the "generative pre-training" of a language model that acquires knowledge of the world by "reading" enormous quantities of written text. The "3" indicates that this is the third generation of the system. GPT-3 is a product of OpenAI, an artificial intelligence research lab based in San Francisco. In essence, it's a machine-learning system that has been fed (trained on) 45 terabytes of text data. Given that a terabyte (TB) is a trillion bytes, that's quite a lot.

Anomalies are occurrences in a dataset that are in some way unusual and do not fit the general patterns. The concept of the anomaly is generally ill-defined and perceived as vague and domain-dependent. Moreover, no comprehensive and concrete overviews of the different types of anomalies have hitherto been published. By means of an extensive literature review this study therefore offers the first theoretically principled and domain-independent typology of data anomalies, and presents a full overview of anomaly types and subtypes. To concretely define the concept of the anomaly and its different manifestations the typology employs four dimensions: data type, cardinality of relationship, data structure and data distribution. These fundamental and data-centric dimensions naturally yield 3 broad groups, 9 basic types and 61 subtypes of anomalies. The typology facilitates the evaluation of the functional capabilities of anomaly detection algorithms, contributes to explainable data science, and provides insights into relevant topics such as local versus global anomalies.