A critical concern in data-driven decision making is to build models whose outcomes do not discriminate against some demographic groups, including gender, ethnicity, or age. To ensure non-discrimination in learning tasks, knowledge of the sensitive attributes is essential, while, in practice, these attributes may not be available due to legal and ethical requirements. To address this challenge, this paper studies a model that protects the privacy of the individuals sensitive information while also allowing it to learn non-discriminatory predictors. The method relies on the notion of differential privacy and the use of Lagrangian duality to design neural networks that can accommodate fairness constraints while guaranteeing the privacy of sensitive attributes. The paper analyses the tension between accuracy, privacy, and fairness and the experimental evaluation illustrates the benefits of the proposed model on several prediction tasks.

"According to the filing, the inventors claimed that capsule networks can be used in place of conventional convolutional neural networks." Looks like Google won't be stopping its infamous patenting spree anytime soon. Earlier this month, Google filed a patent for capsule networks. Turing award recipient and Google researcher Geoff Hinton was named amongst the list of inventors in the filing. According to the patent filed, the inventors claimed that capsule networks can be used in place of conventional convolutional neural networks for traditional computer vision applications. Capsule networks are aimed at alleviating the extra dimensionality which surfaces with a convolutional neural network.

The book will consist of contributions based on some of Leiden University's SAILS research project's results and your contribution as a leading expert in this area. We invite contributions focusing on technological, legal, ethical, or social issues of the development and use of AI. Topics are not limited to those mentioned in the call for papers. This may concern best practices in regulating AI, in using AI in the legal domain, or any assessment frameworks for AI developments. All papers will be peer-reviewed by our program committee and other independent reviewers (where necessary) and will be published in an edited book with an ISBN.

During this period of progressive development and deployment of artificial intelligence, discussions around the ethical, legal, socio-economic and cultural implications of its use are increasing. What are the challenges and the strategy, and what are the values that Europe can bring to this domain? During the European Conference on AI (ECAI 2020), two special events in the format of panels discussed the challenges of AI made in the European Union, the shape of future research and industry, and the strategy to retain talent and compete with other world powers. This article collects some of the main messages from these two sessions, which included the participation of AI experts from leading European organisations and networks. Since the publication of European directives and guidance, such as the EC White Paper on AI and the Trustworthy AI Guidelines, Europe has been laying the foundation for the future vision of AI. The European strategy for AI builds on the well-known and accepted principles found in the Charter of Fundamental Rights of the European Commission and the Universal Declaration of Human Rights to define a human-centric approach, whose primary purpose is to enhance human capabilities and societal well-being.

Massachusetts State Police (MSP) has been quietly testing ways to use the four-legged Boston Dynamics robot known as Spot, according to new documents obtained by the American Civil Liberties Union of Massachusetts. And while Spot isn't equipped with a weapon just yet, the documents provide a terrifying peek at our RoboCop future. This browser does not support the video element. The Spot robot, which was officially made available for lease to businesses last month, has been in use by MSP since at least April 2019 and has engaged in at least two police "incidents," though it's not clear what those incidents may have been. It's also not clear whether the robots were being operated by a human controller or how much autonomous action the robots are allowed.

It enables financial institutions to simplify identifying illicit client relationships, beneficiaries, and links to criminal or terrorist activity during the onboarding phase. FREMONT, CA: Financial regulations globally are cracking down on banks. As Anti Money Laundering and know your customer (KYC) procedures are getting stricter, hefty fines are being imposed on those found to be in breach of the same. Recent studies have discovered that banks across the globe have been charged with a total of USD 26 billion in monetary penalties in Anti Money Laundering (AML) and sanctions violations over the last ten years. As banks and financial institutions continue to search for digital transformation initiatives to streamline and simplify the customer onboarding process and reduce the risk associated with fraud, many are looking to exploit emerging technologies' potential.

Patents are used to grant exclusive property rights to an inventor and prevent their discovery from being copied by others. The main requirements for a patent are that the invention must be novel, non-obvious and be useful or have an industrial application. Patents are a central part of how pharma does business. Pharma products require longer and more complex research and development (R&D) cycles than products in other industries. Consequently, companies invest significant amounts of money into their new products early on in their development.

Using a weightless neural network architecture WiSARD we propose a straightforward graph to retina codification to represent business process graph flows avoiding kernels, and we present how WiSARD outperforms the classification performance with small training sets in the process mining context.

Event forecasting is a challenging, yet consequential task, as humans seek to constantly plan for the future. Existing automated forecasting approaches rely mostly on structured data, such as time-series or event-based knowledge graphs, to help predict future events. In this work, we formulate the forecasting problem as a restricted-domain, multiple-choice, question-answering (QA) task that simulates the forecasting scenario. To showcase the usefulness of this task formulation, we introduce a dataset ForecastQA, a question-answering dataset consisting of 10,392 event forecasting questions, which have been collected and verified via crowdsourcing efforts. We also present our experiments on ForecastQA using BERT-based models and find that our best model achieves 61.0\% accuracy on the dataset, which is still far behind human performance by about 18%. We hope ForecastQA will support future research efforts in bridging this gap.

Lyrics parody swaps one set of words that accompany a melody with a new set of words, preserving the number of syllables per line and the rhyme scheme. Lyrics parody generation is a challenge for controllable text generation. We show how a specialized sampling procedure, combined with backward text generation with XLNet can produce parody lyrics that reliably meet the syllable and rhyme scheme constraints. We introduce the Weird AI Yankovic system and provide a case study evaluation. We conclude with societal implications of neural lyric parody generation.