As technology becomes more advanced, those who design, use and are otherwise affected by it want to know that it will perform correctly, and understand why it does what it does, and how to use it appropriately. In essence they want to be able to trust the systems that are being designed. In this survey we present assurances that are the method by which users can understand how to trust autonomous systems. Trust between humans and autonomy is reviewed, and the implications for the design of assurances are highlighted. A survey of existing research related to assurances is presented. Much of the surveyed research originates from fields such as interpretable, comprehensible, transparent, and explainable machine learning, as well as human-computer interaction, human-robot interaction, and e-commerce. Several key ideas are extracted from this work in order to refine the definition of assurances. The design of assurances is found to be highly dependent not only on the capabilities of the autonomous system, but on the characteristics of the human user, and the appropriate trust-related behaviors. Several directions for future research are identified and discussed.

In many settings, it is important that a model be capable of providing reasons for its predictions (i.e., the model must be interpretable). However, the model's reasoning may not conform with well-established knowledge. In such cases, while interpretable, the model lacks \textit{credibility}. In this work, we formally define credibility in the linear setting and focus on techniques for learning models that are both accurate and credible. In particular, we propose a regularization penalty, expert yielded estimates (EYE), that incorporates expert knowledge about well-known relationships among covariates and the outcome of interest. We give both theoretical and empirical results comparing our proposed method to several other regularization techniques. Across a range of settings, experiments on both synthetic and real data show that models learned using the EYE penalty are significantly more credible than those learned using other penalties. Applied to a large-scale patient risk stratification task, our proposed technique results in a model whose top features overlap significantly with known clinical risk factors, while still achieving good predictive performance.

In this paper, we study deep signal representations that are invariant to groups of transformations and stable to the action of diffeomorphisms without losing signal information. This is achieved by generalizing the multilayer kernel construction introduced in the context of convolutional kernel networks and by studying the geometry of the corresponding reproducing kernel Hilbert space. We show that the signal representation is stable, and that models from this functional space, such as a large class of convolutional neural networks with homogeneous activation functions, may enjoy the same stability. In particular, we study the norm of such models, which acts as a measure of complexity, controlling both stability and generalization.

This preprint has been reviewed and recommended by Peer Community In Evolutionary Biology (http://dx.doi.org/10.24072/pci.evolbiol.100036). Approximate Bayesian computation (ABC) has grown into a standard methodology that manages Bayesian inference for models associated with intractable likelihood functions. Most ABC implementations require the preliminary selection of a vector of informative statistics summarizing raw data. Furthermore, in almost all existing implementations, the tolerance level that separates acceptance from rejection of simulated parameter values needs to be calibrated. We propose to conduct likelihood-free Bayesian inferences about parameters with no prior selection of the relevant components of the summary statistics and bypassing the derivation of the associated tolerance level. The approach relies on the random forest methodology of Breiman (2001) applied in a (non parametric) regression setting. We advocate the derivation of a new random forest for each component of the parameter vector of interest. When compared with earlier ABC solutions, this method offers significant gains in terms of robustness to the choice of the summary statistics, does not depend on any type of tolerance level, and is a good trade-off in term of quality of point estimator precision and credible interval estimations for a given computing time. We illustrate the performance of our methodological proposal and compare it with earlier ABC methods on a Normal toy example and a population genetics example dealing with human population evolution. All methods designed here have been incorporated in the R package abcrf (version 1.7) available on CRAN.

We used redescription mining to find interpretable rules revealing associations between those determinants that provide insights about the Alzheimer's disease (AD). We extended the CLUS-RM redescription mining algorithm to a constraint-based redescription mining (CBRM) setting, which enables several modes of targeted exploration of specific, user-constrained associations. Redescription mining enabled finding specific constructs of clinical and biological attributes that describe many groups of subjects of different size, homogeneity and levels of cognitive impairment. We confirmed some previously known findings. However, in some instances, as with the attributes: testosterone, the imaging attribute Spatial Pattern of Abnormalities for Recognition of Early AD, as well as the levels of leptin and angiopoietin-2 in plasma, we corroborated previously debatable findings or provided additional information about these variables and their association with AD pathogenesis. Applying redescription mining on ADNI data resulted with the discovery of one largely unknown attribute: the Pregnancy-Associated Protein-A (PAPP-A), which we found highly associated with cognitive impairment in AD. Statistically significant correlations (p <= 0.01) were found between PAPP-A and various different clinical tests. The high importance of this finding lies in the fact that PAPP-A is a metalloproteinase, known to cleave insulin-like growth factor binding proteins. Since it also shares similar substrates with A Disintegrin and the Metalloproteinase family of enzymes that act as {\alpha}-secretase to physiologically cleave amyloid precursor protein (APP) in the non-amyloidogenic pathway, it could be directly involved in the metabolism of APP very early during the disease course. Therefore, further studies should investigate the role of PAPP-A in the development of AD more thoroughly.

The setup is as follows: given an episodic task and a finite number of off-policy RL algorithms, a meta-algorithm has to decide which RL algorithm is in control during the next episode so as to maximize the expected return. The article presents a novel meta-algorithm, called Epochal Stochastic Bandit Algorithm Selection (ESBAS). Its principle is to freeze the policy updates at each epoch, and to leave a rebooted stochastic bandit in charge of the algorithm selection. Under some assumptions, a thorough theoretical analysis demonstrates its near-optimality considering the structural sampling budget limitations. ESBAS is first empirically evaluated on a dialogue task where it is shown to outperform each individual algorithm in most configurations. ESBAS is then adapted to a true online setting where algorithms update their policies after each transition, which we call SSBAS. SSBAS is evaluated on a fruit collection task where it is shown to adapt the stepsize parameter more efficiently than the classical hyperbolic decay, and on an Atari game, where it improves the performance by a wide margin.

Mr. Matusiak is an expert in the fields of mathematics, programming, and music theory. Mr. Matusiak's groundbreaking application of advanced artificial intelligence algorithms for the analysis, transformation and creation of music forms the basis of DigiTrax's disruptive approach to music composition, and has generated six granted patents. As the software architect of The Music Builder platform, his pioneering vision is grounded in both theoretical and practical knowledge of music theory. Mr. Matusiak has garnered multiple awards in the field, while completing his studies at Leeds College of Music in the UK. As Co-founder and Lead Developer for Exomens, Ltd., Mr. Matusiak researched, designed, and implemented multiple large-scale artificial intelligence projects, including systems for music, audio, and naturallanguage analysis.

German engineers have unveiled an ultra-futuristic train with noise cancelling chairs, tablet stands, games consoles and even a gym as a rival to self-driving cars. The'Ideenzug' or'Idea Train' was presented by railway firm Deutsche Bahn at an exhibition in the city of Nuremberg as part of moves to revolutionise morning commutes. Features on board the double-decker train include chairs that swivel to face either direction, television screens and pods set aside for'power napping'. Rail firms hope the design will rival self-driving cars, which are expected to be popular among those who want to take their mind off their daily commute. Features on board the double-decker train include chairs that swivel to face either direction, television screens and pods set aside for'power napping' (pictured) Jörg Sandvoß, head of Deutsche Bahn Regio, told Süddeutsche Zeitung that car makers want to create'rolling living rooms' and train companies need to come up with even better options.

Artificial Intelligence has been a hot word across all industries lately. Think all the fuss around self-driving cars, Google's updated Assistant and the general talks of how conversational interfaces are the future of tech. Around 54 percent of retailers already use or plan to add artificial intelligence technology to their toolkit, with 20 percent planning to introduce some AI within the next 12 months, according to the latest report from SLI Systems. The increased adoption of AI in retail can be specifically attributed to advances in the deep learning. Deep learning is a specific machine learning approach to building and training neural networks.

Police in the US state of Delaware are poised to deploy'smart' cameras in cruisers to help authorities detect a vehicle carrying a fugitive, missing child or straying senior. The video feeds will be analyzed using artificial intelligence to identify vehicles by license plate or other features and'give an extra set of eyes' to officers on patrol, says David Hinojosa of Coban Technologies, the company providing the equipment. 'We are helping officers keep their focus on their jobs,' said Hinojosa, who touts the new technology as a'dashcam on steroids.' The program is part of a growing trend to use vision-based AI to thwart crime and improve public safety, a trend which has stirred concerns among privacy and civil liberties activists who fear the technology could lead to secret'profiling' and misuse of data. US-based startup Deep Science is using the same technology to help retail stores detect in real time if an armed robbery is in progress, by identifying guns or masked assailants.