Separate from the two main camps in ethics, deontological ethics (D) and consequentialism (C), there is virtue ethics (V). While there has been extensive formal, computational, and mathematical work done on deontological ethics and consequentialism, there has been very little or almost no work done in formalizing and making rigorous virtue ethics. Proponents of V might claim that it is not feasible to do so given V's emphasis on character and traits, rather than individual actions or consequencens. From the perspective of machine and robot ethics, this is not satisfactory. If V is to be considered to be on equal footing with D and C for the purpose of building morally competent machines, we need to start with formalizing parts of virtue ethics.

Skills learned through (deep) reinforcement learning often generalizes poorly across domains and re-training is necessary when presented with a new task. We present a framework that combines techniques in \textit{formal methods} with \textit{reinforcement learning} (RL). The methods we provide allows for convenient specification of tasks with logical expressions, learns hierarchical policies (meta-controller and low-level controllers) with well-defined intrinsic rewards, and construct new skills from existing ones with little to no additional exploration. We evaluate the proposed methods in a simple grid world simulation as well as a more complicated kitchen environment in AI2Thor

An explorative data analysis system should be aware of what the user already knows and what the user wants to know of the data: otherwise the system cannot provide the user with the most informative and useful views of the data. We propose a principled way to do explorative data analysis, where the user's background knowledge is modeled by a distribution parametrised by subsets of rows and columns in the data, called tiles. The user can also use tiles to describe his or her interests concerning relations in the data. We provide a computationally efficient implementation of this concept based on constrained randomisation. This is used to model both the background knowledge and the user's information request and is a necessary prerequisite for any interactive system. Furthermore, we describe a novel linear projection pursuit method to find and show the views most informative to the user, which at the limit of no background knowledge and with generic objective reduces to PCA. We show that our method is robust under noise and fast enough for interactive use. We also show that the method gives understandable and useful results when analysing real-world data sets. We will release, under an open source license, a software library implementing the idea, including the experiments presented in this paper. We show that our method can outperform standard projection pursuit visualisation methods in exploration tasks. Our framework makes it possible to construct human-guided data exploration systems which are fast, powerful, and give results that are easy to comprehend.

This tutorial discusses some powerful techniques which can be used to build artificial intelligent (AI) systems which act rational in the sense of following an overarching goal. AI Principle: Based on the perceived environment, compute actions ( decisions) in order to maximize a long-term return. The actual implementation of this principle requires, of course, to have a precise definition for what is meant by "perceived environment", "actions" and "return". We highlight that those definitions are essentially a design choice which have to be made by an AI scientist or engineer which is facing a particular application domain. Let us consider some application domains where AI systems could be used (beneficially?): - a routing app for Helsinki (similar to https://www.reittiopas.fi/):

In this paper, we introduce Attentive Guidance (AG), a new mechanism to direct a sequence to sequence model equipped with attention to find more compositional solutions that generalise even in cases where the training and testing distribution strongly diverge. We test AG on two tasks, devised precisely to asses the composi- tional capabilities of neural models and show how vanilla sequence to sequence models with attention overfit the training distribution, while the guided versions come up with compositional solutions that, in some cases, fit the training and testing distributions equally well. AG is a simple and intuitive method to provide a learning bias to a sequence to sequence model without the need of including extra components, that we believe allows to inject a component in the training process which is also present in human learning: guidance.

In this letter, we briefly review the basic scheme of the pseudoinverse learning (PIL) algorithm and present some discussions on the PIL, as well as its variants. The PIL algorithm, first presented in 1995, is a non-gradient descent algorithm for multi-layer neural networks and has several advantages compared with gradient descent based algorithms. We also show that the so-called extreme learning machine (ELM) is a vest (another name) of the PIL algorithm for single hidden layer feedforward neural networks.

This paper presents a locally decoupled network parameter learning with local propagation. Three elements are taken into account: (i) sets of nonlinear transforms that describe the representations at all nodes, (ii) a local objective at each node related to the corresponding local representation goal, and (iii) a local propagation model that relates the nonlinear error vectors at each node with the goal error vectors from the directly connected nodes. The modeling concepts (i), (ii) and (iii) offer several advantages, including (a) a unified learning principle for any network that is represented as a graph, (b) understanding and interpretation of the local and the global learning dynamics, (c) decoupled and parallel parameter learning, (d) a possibility for learning in infinitely long, multi-path and multi-goal networks. Numerical experiments validate the potential of the learning principle. The preliminary results show advantages in comparison to the state-of-the-art methods, w.r.t. the learning time and the network size while having comparable recognition accuracy.

Over the years, almost every organization has understood the importance of analyzing data. In fact, it would not be an overstatement to say that "No organization will be able to survive today's cut-throat competition if it does not analyze data." Data analysis as we know it is the process of taking the source data, refining it to get useful information, and then making useful predictions from it. In this Learning Path, we will learn how to analyze data using the powerful toolset provided by Python. Packt's Video Learning Paths are a series of individual video products put together in a logical and stepwise manner such that each video builds on the skills learned in the video before it.

Discovering just how many people that post reached is no longer just for big brands -- using artificial intelligence and more than two dozen different data points, Skorr is a new app that measures social media influence across multiple channels for individuals and small businesses. Launching on the App Store and Google Play on Monday, May 7, Skorr measures and monitors social media influence, along with delivering suggestions for improvements and creating social challenges among friends. The app is from developer Slaicos Lda, a start-up based in Portugal that recently passed the one-year mark. Skorr will measure and analyze influence from six of the major platforms -- Twitter, Facebook, LinkedIn, Instagram, Tumbler, and YouTube -- to give users a Skorr index based on a scale of 1 to 100. While a number of programs work to measure social media impact, Skorr uses both data and artificial intelligence to offer social insight.

In an effort to keep up with the demands of the digital world, Gatwick has recently announced the modernization its IT infrastructure, in partnership with Hewlett Packard Enterprise and Aruba. Even though typical IT upgrades in airports take four years, Gatwick's network was upgraded in just 18 months, all while avoiding downtime and instability. Work was completed overnight with just a 2 hour window for upgrades and 2 hours to roll back to the legacy network. Data links were limited with Gatwick's old IT infrastructure, but the net network contains a cleaner meshed design providing up to 10 times more data connections. As new technologies continue emerging for consumers, the airport's management, and the airlines as well as businesses in the airport who rely on their infrastructure, Gatwick will provide a robust backbone.