The application of Deep Neural Networks (DNNs) to a broad variety of tasks demands methods for coping with the complex and opaque nature of these architectures. The analysis of performance can be pursued in two ways. On one side, model interpretation techniques aim at "opening the box" to assess the relationship between the input, the inner layers, and the output. For example, saliency and attention models exploit knowledge of the architecture to capture the essential regions of the input that have the most impact on the inference process and output. On the other hand, models can be analysed as "black boxes", e.g., by associating the input samples with extra annotations that do not contribute to model training but can be exploited for characterizing the model response. Such performance-driven meta-annotations enable the detailed characterization of performance metrics and errors and help scientists identify the features of the input responsible for prediction failures and focus their model improvement efforts. This paper presents a structured survey of the tools that support the "black box" analysis of DNNs and discusses the gaps in the current proposals and the relevant future directions in this research field.

While the need for well-trained, fair ML systems is increasing ever more, measuring fairness for modern models and datasets is becoming increasingly difficult as they grow at an unprecedented pace. One key challenge in scaling common fairness metrics to such models and datasets is the requirement of exhaustive ground truth labeling, which cannot always be done. Indeed, this often rules out the application of traditional analysis metrics and systems. At the same time, ML-fairness assessments cannot be made algorithmically, as fairness is a highly subjective matter. Thus, domain experts need to be able to extract and reason about bias throughout models and datasets to make informed decisions. While visual analysis tools are of great help when investigating potential bias in DL models, none of the existing approaches have been designed for the specific tasks and challenges that arise in large label spaces. Addressing the lack of visualization work in this area, we propose guidelines for designing visualizations for such large label spaces, considering both technical and ethical issues. Our proposed visualization approach can be integrated into classical model and data pipelines, and we provide an implementation of our techniques open-sourced as a TensorBoard plug-in. With our approach, different models and datasets for large label spaces can be systematically and visually analyzed and compared to make informed fairness assessments tackling problematic bias.

Supervised classification techniques use training samples to learn a classification rule with small expected 0-1-loss(error probability). Conventional methods enable tractable learning and provide out-of-sample generalization by using surrogate losses instead of the 0-1-loss and considering specific families of rules (hypothesis classes). This paper presents minimax risk classifiers (MRCs) that minimize the worst-case 0-1-loss over general classification rules and provide tight performance guarantees at learning. We show that MRCs are strongly universally consistent using feature mappings given by characteristic kernels. The paper also proposes efficient optimization techniques for MRC learning and shows that the methods presented can provide accurate classification together with tight performance guarantees.

Jeff Lipniskis describes his role at PPG as having line-of-business IT responsibilities. As global director information technology, architectural coatings & Latin America, he reports to the corporate CIO and has accountability for IT globally in the company's architectural coatings business, leads IT for its protective and marine coatings, and has oversight for IT within the company's research and development organization. A 21-year veteran at PPG, Lipniskis has experienced a significant portfolio transformation and globalization of the company. In his two decades at PPG, the company has made over 60 acquisitions and has roughly doubled in size in terms of sales. Today, PPG is the world's largest manufacturer of paints and coatings, operating in 65 countries around the world.

This work studies a dynamic mechanism design problem in which a principal delegates decision makings to a group of privately-informed agents without the monetary transfer or burning. We consider that the principal privately possesses complete knowledge about the state transitions and study how she can use her private observation to support the incentive compatibility of the delegation via informational burning, a process we refer to as the looking-forward persuasion. The delegation mechanism is formulated in which the agents form belief hierarchies due to the persuasion and play a dynamic Bayesian game. We propose a novel randomized mechanism, known as Bayesian promised delegation (BPD), in which the periodic incentive compatibility is guaranteed by persuasions and promises of future delegations. We show that the BPD can achieve the same optimal social welfare as the original mechanism in stationary Markov perfect Bayesian equilibria. A revelation-principle-like design regime is established to show that the persuasion with belief hierarchies can be fully characterized by correlating the randomization of the agents' local BPD mechanisms with the persuasion as a direct recommendation of the future promises.

Most software companies have extensive test suites and re-run parts of them continuously to ensure recent changes have no adverse effects. Since test suites are costly to execute, industry needs methods for test case prioritisation (TCP). Recently, TCP methods use machine learning (ML) to exploit the information known about the system under test (SUT) and its test cases. However, the value added by ML-based TCP methods should be critically assessed with respect to the cost of collecting the information. This paper analyses two decades of TCP research, and presents a taxonomy of 91 information attributes that have been used. The attributes are classified with respect to their information sources and the characteristics of their extraction process. Based on this taxonomy, TCP methods validated with industrial data and those applying ML are analysed in terms of information availability, attribute combination and definition of data features suitable for ML. Relying on a high number of information attributes, assuming easy access to SUT code and simplified testing environments are identified as factors that might hamper industrial applicability of ML-based TCP. The TePIA taxonomy provides a reference framework to unify terminology and evaluate alternatives considering the cost-benefit of the information attributes.

Probabilistic models often use neural networks to control their predictive uncertainty. However, when making out-of-distribution (OOD)} predictions, the often-uncontrollable extrapolation properties of neural networks yield poor uncertainty predictions. Such models then don't know what they don't know, which directly limits their robustness w.r.t unexpected inputs. To counter this, we propose to explicitly train the uncertainty predictor where we are not given data to make it reliable. As one cannot train without data, we provide mechanisms for generating pseudo-inputs in informative low-density regions of the input space, and show how to leverage these in a practical Bayesian framework that casts a prior distribution over the model uncertainty. With a holistic evaluation, we demonstrate that this yields robust and interpretable predictions of uncertainty while retaining state-of-the-art performance on diverse tasks such as regression and generative modelling

The digital educational solutions are increasingly used demanding high quality functionalities. In this sense, standards and models are made available by governments, associations, and researchers being most used in quality control and assessment sessions. The eQETIC model was built according to the approach of continuous process improvement favoring the quality management for development and maintenance of digital educational solutions. This article presents two expert systems to support the implementation of eQETIC model and demonstrates that such systems are able to support users during the model implementation. Developed according to two types of shells (SINTA/UFC and e2gLite/eXpertise2go), the systems were used by a professional who develops these type of solutions and showed positive results regarding the support offered by them in implementing the rules proposed by eQETIC model.

A set of steps for implementing a chatbot, to support decision-making activities in the software incident management process is proposed and discussed in this article. Each step is presented independently of the platform used for the construction of chatbots and are detailed with their respective activities. The proposed steps can be carried out in a continuous and adaptable way, favoring the constant training of a chatbot and allowing the increasingly cohesive interpretatin of the intentions of the specialists who work in the Software Incident Management Process. The software incident resolution process accordingly to the ITIL framework, is considered for the experiment. The results of the work present the steps for the chatbot construction, the solution based on DialogFlow platform and some conclusions based on the experiment.

According to a new survey, six out of ten expect that products and services using artificial intelligence will profoundly change their daily life in the next three to five years and half feel that this has already happened. These are some of the findings of a 28-country survey conducted by Ipsos for the World Economic Forum of 19,504 adults under the age of 75 between November 19 and December 3, 2021. "In order to trust artificial intelligence, people must know and understand exactly what AI is, what it's doing, and its impact," said Kay Firth-Butterfield, Head of Artificial Intelligence and Machine Learning at the World Economic Forum. "Leaders and companies must make transparent and trustworthy AI a priority as they implement this technology. At the World Economic Forum, we are focused on multistakeholder collaboration to optimize accountability, transparency, privacy and impartiality to create that trust. With the ability to solve many of society's pressing issues, we are focused on accelerating the benefits and mitigating the risks of artificial intelligence and machine learning. Only then can we gain public trust and benefit from the rewards of emerging tech like AI."