We consider the problem of providing users of deep Reinforcement Learning (RL) based systems with a better understanding of when their output can be trusted. We offer an explainable artificial intelligence (XAI) framework that provides a three-fold explanation: a graphical depiction of the systems generalization and performance in the current game state, how well the agent would play in semantically similar environments, and a narrative explanation of what the graphical information implies. We created a user-interface for our XAI framework and evaluated its efficacy via a human-user experiment. The results demonstrate a statistically significant increase in user trust and acceptance of the AI system with explanation, versus the AI system without explanation.

When faced with learning challenging new tasks, humans often follow sequences of steps that allow them to incrementally build up the necessary skills for performing these new tasks. However, in machine learning, models are most often trained to solve the target tasks directly.Inspired by human learning, we propose a novel curriculum learning approach which decomposes challenging tasks into sequences of easier intermediate goals that are used to pre-train a model before tackling the target task. We focus on classification tasks, and design the intermediate tasks using an automatically constructed label hierarchy. We train the model at each level of the hierarchy, from coarse labels to fine labels, transferring acquired knowledge across these levels. For instance, the model will first learn to distinguish animals from objects, and then use this acquired knowledge when learning to classify among more fine-grained classes such as cat, dog, car, and truck. Most existing curriculum learning algorithms for supervised learning consist of scheduling the order in which the training examples are presented to the model. In contrast, our approach focuses on the output space of the model. We evaluate our method on several established datasets and show significant performance gains especially on classification problems with many labels. We also evaluate on a new synthetic dataset which allows us to study multiple aspects of our method.

K-Nearest Neighbors (KNN) search is a fundamental algorithm in artificial intelligence software with applications in robotics, and autonomous vehicles. These wide-ranging applications utilize KNN either directly for simple classification or combine KNN results as input to other algorithms such as Locally Weighted Learning (LWL). Similar to binary trees, kd-trees become unbalanced as new data is added in online applications which can lead to rapid degradation in search performance unless the tree is rebuilt. Although approximate methods are suitable for graphics applications, which prioritize query speed over query accuracy, they are unsuitable for certain applications in autonomous systems, aeronautics, and robotic manipulation where exact solutions are desired. In this paper, we will attempt to assess the performance of non-recursive deterministic kd-tree functions and KNN functions. We will also present a "forest of interval kd-trees" which reduces the number of tree rebuilds, without compromising the exactness of query results.

In the new era of very large telescopes, where data is crucial to expand scientific knowledge, we have witnessed many deep learning applications for the automatic classification of lightcurves. Recurrent neural networks (RNNs) are one of the models used for these applications, and the LSTM unit stands out for being an excellent choice for the representation of long time series. In general, RNNs assume observations at discrete times, which may not suit the irregular sampling of lightcurves. A traditional technique to address irregular sequences consists of adding the sampling time to the network's input, but this is not guaranteed to capture sampling irregularities during training. Alternatively, the Phased LSTM unit has been created to address this problem by updating its state using the sampling times explicitly. In this work, we study the effectiveness of the LSTM and Phased LSTM based architectures for the classification of astronomical lightcurves. We use seven catalogs containing periodic and nonperiodic astronomical objects. Our findings show that LSTM outperformed PLSTM on 6/7 datasets. However, the combination of both units enhances the results in all datasets.

We introduce 3DB: an extendable, unified framework for testing and debugging vision models using photorealistic simulation. We demonstrate, through a wide range of use cases, that 3DB allows users to discover vulnerabilities in computer vision systems and gain insights into how models make decisions. 3DB captures and generalizes many robustness analyses from prior work, and enables one to study their interplay. Finally, we find that the insights generated by the system transfer to the physical world. We are releasing 3DB as a library (https://github.com/3db/3db) alongside a set of example analyses, guides, and documentation: https://3db.github.io/3db/ .

Current methods focus on manifolds that are topologically Euclidean, enforce strong structural priors on the learned models or use operations that do not scale to high dimensions. In contrast, our model learns the local manifold topology piecewise by "gluing" it back together through a collection of learned coordinate charts. We demonstrate the efficiency of our approach on synthetic data of known manifolds, as well as higher dimensional manifolds of unknown topology, where we show better sample efficiency and competitive or superior performance against current state-of-the-art.

First came the idea of making Covid vaccinations mandatory to go to the pub, while Israel offered free pizza and beer with a shot. Now UK officials have hit on what they hope is an even more persuasive reason for young people to get their jab: more chance of getting a date. In an eye-catching policy coinciding with the rollout of vaccinations for the under-30s beginning this week, the Department of Health and Social Care (DHSC) has teamed up with popular dating apps to encourage take-up of the programme. Users of Tinder, Match, Hinge, Bumble, Badoo, Plenty of Fish, OurTime and Muzmatch will enjoy a series of benefits if they add their vaccination status to their profile, including virtual badges and stickers. Most of the apps are also giving people who say they have been vaccinated free bonuses such as a certain number of "boosts", which promote their profile to potential dates, offering the tantalising prospect of a greater stake in what has already been billed a post-pandemic "summer of love".

Erich Schweighofer is Professor of Legal Informatics, International Law and European Law and head of the Centre for Computers and Law at the University of Vienna. He leads the Centre for Computers and Law – one of the top – 10 research groups in Legal Informatics worldwide. Erich Schweighofer is an international expert in legal informatics and internet governance. He has been involved in many research projects, above all, text analysis, data protection, surveillance technologies and IT security. He is also one of the main organiser of IRIS – a Legal Informatics symposium – and is also active at OCG, GI, CEPIS, IAAIL, FALM and ICANN, where he is now a member of the EURALO board and theCCWG Accountability.

Organizations that contributed to the report include representatives from arXiv, AI Ethics Lab, Black in AI, Bloomberg Government, Burning Glass Technologies, Computing Research Association, Elsevier, Intento, International Federation of Robotics, Joint Research Center, European Commission, LinkedIn, Liquidnet, McKinsey Global Institute, Microsoft Academic Graph, National Institute of Standards and Technology, Nesta, NetBase Quid, PostEra, Queer in AI, State of AI Report, Women in Machine Learning, and many individual contributors. Supporting partners to the report include McKinsey & Company, Google, OpenAI, Genpact, AI21 labs, and PricewaterhouseCoopers.

While the ongoing pandemic and subsequent nationwide lockdowns have been prime reasons for stress on the overall economy, the Digital India movement initiated by the government of India remained pivotal in providing a push to Industry 4.0 or the application of Advanced Digital Production (ADP) technologies. Industry 4.0 is a complete revolution of old technologies with more automation, artificial intelligence (AI) and also bridging the gap between physical and digital world by enabling Internet of Things (IoT). The current trend of digital transformation has a vision of reaching the stage where one can enable the autonomous decision-making, monitor assets, value creation process as well as vertical, horizontal integration. Industry 4.0 Applications No doubt, there are industries which have already started preparing themselves for the Industry 4.0 and future, where smart manufacturing can enhance their business. However, there are some which are still denying or struggling to know how industry 4.0 can impact their business in the best manner as well as to find the talent respectively.