A Knowledge Graph (KG), popularly used in both industry and academia, is an effective representation of knowledge. It consists of a collection of knowledge elements, each of which in turn is extracted from the web or other sources. Information extractors that use natural language processing techniques or other complex algorithms are usually noisy. That is, the vast number of knowledge elements extracted from the web may not only be associated with different confidence values but may also be inconsistent with each other. Many applications such as question answering systems that are built on top of large-scale KGs are required to reason efficiently about these confidence values and inconsistencies. In addition, they are required to incorporate ontological constraints in their reasoning. One way to do this is to extract a subgraph of a KG that is consistent with the ontological constraints and is of maximum total confidence value. Such a subgraph is referred to as the top hypothesis and is combinatorially hard to find. In this paper, we introduce an algorithmic framework for efficiently addressing the combinatorial hardness and selecting the top K hypotheses. Our approach is based on powerful algorithmic techniques recently invented in the context of the Weighted Constraint Satisfaction Problem (WCSP).

This paper examines the effect of providing adversarial labels to several algorithms that use noisy labels from multiple experts to estimate classifier accuracy, referred to hereafter as "estimators." We propose four adversary labeling strategies and use experiments on synthetic data to gauge their impact on the estimators. Our results show that even a single adversary can considerably impact the effectiveness of an estimator. In addition, we find that estimators that weight the input of all experts equally tend to be much more affected by the inclusion of adversaries than those that can separately model each expert and that the impact of adversaries is lessened when the experts have higher accuracy.

Auditing algorithms has emerged as a methodology for holding algorithms accountable by testing whether they are fair. This process often relies on the repeated use of a platform to record inputs and their corresponding outputs. For example, to audit Google search, one repeatedly inputs queries and captures the received search pages. The goal is then to discover, in the collected data, patterns that will reveal the ``secrets'' of algorithmic decision making. This knowledge discovery process makes some algorithm auditing tasks great applications for data mining techniques. In this paper, we introduce one particular algorithm audit, that of Google's Top stories. We describe the process of data collection, exploration, and analysis for this application and share some of the gleaned insights. Concretely, our analysis suggests that Google might be trying to burst the famous ``filter bubble'' by choosing less known publishers for the 3rd position in the Top stories.

We examine the ability of a genetic algorithm to learn a predictive model that can estimate the likelihood that a physical therapist will receive annual Medicare payments above or below the industry median based on the physical therapist's practice parameters. We compare the performance of a canonical genetic algorithm and a self adaptive genetic algorithm with the performance of traditional logistic regression. Results show that both genetic algorithm approaches are competitive with logistic regression with the canonical genetic algorithm consistently outperforming logistic regression.

Attacks — on the recent Wi-Fi Direct standard developed for IoT devices — that exploit the high power consumption required for the group owner function are addressed here by introducing intelligent decision making into the group owner negotiation process. The Wi-Fi Direct standard was introduced with the intention of simplifying peer-to-peer connections in home applications while helping devices to save power by centralizing effort into a single group owner device negotiated on start-up. Attacks on the group formation stage can be based on manipulating a victim device to frequently end up being assigned the group owner function, thereby depleting its batteries at faster rates than its peer devices. This manipulation is made easy by the group formation process adopted by the standard. We propose to enhance the group formation process with secure features ensuring fairness by relying on commitments and learning about the behavior observed for peer devices in the past. Simulations are used to quantify the resistance achieved against several attack strategies.

We propose a concept map based approach to assessing freely generated student responses. The proposed approach is based on a novel automated tuple extraction system, DT-OpenIE, for automatically extracting concept maps from student responses. The DT-OpenIE system is significantly better in terms of concept map quality for assessment purposes than state-of-the-art open information extraction (IE) systems such as Ollie or Stanford as evidenced by our experimental results. The concept map based approach can significantly improve tracking student's mastery level in an automated tutoring environment such as DeepTutor where students interact with the automated tutor using natural language because the concept maps can be used not only to generate a holistic score assessing the accuracy of a student response but also enable diagnostic feedback.

Recent progress in AI and Reinforcement learning has shown great success in solving complex problems with high dimensional state spaces. However, most of these successes have been primarily in simulated environments where failure is of little or no consequence. Most real-world applications, however, require training solutions that are safe to operate as catastrophic failures are inadmissible especially when there is human interaction involved. Currently, Safe RL systems use human oversight during training and exploration in order to make sure the RL agent does not go into a catastrophic state. These methods require a large amount of human labor and it is very difficult to scale up. We present a hybrid method for reducing the human intervention time by combining model-based approaches and training a supervised learner to to improve sample efficiency while also ensuring safety. We evaluate these methods on various grid-world environments using both standard and visual representations and show that our approach achieves better performance in terms of sample efficiency, number of catastrophic states reached as well as overall task performance compared to traditional model-free approaches.

However, in recent years symbolic AI has been complemented and sometimes replaced by (Deep) Neural Networks and Machine Learning (ML) techniques. This has vastly increased its potential utility and impact on society, with the consequence that the ethical debate has gone mainstream. Such a debate has primarily focused on principles--the'what' of AI ethics (beneficence, non-maleficence, autonomy, justice and explicability)--rather than on practices, the'how.' Awareness of the potential issues is increasing at a fast rate, but the AI community's ability to take action to mitigate the associated risks is still at its infancy. Therefore, our intention in presenting this research is to contribute to closing the gap between principles and practices by constructing a typology that may help practically-minded developers'apply ethics' at each stage of the pipeline, and to signal to researchers where further work is needed. The focus is exclusively on Machine Learning, but it is hoped that the results of this research may be easily applicable to other branches of AI. The article outlines the research method for creating this typology, the initial findings, and provides a summary of future research needs.

South Korea is developing robots that mimic wildlife adapted for all environments on Earth for military warfare. The nature inspired technology, known as biomimetics, will form part of the country's future weapons systems and help its soldiers in battles. Robot designs inspired by birds, snakes and marine species aim to cover both surveillance and combat via sea, land and sky. It is an attempt to catch up with neighbouring countries such as China and Russia who have made huge advances in the application of the technology, said a defence agency personnel. South Korea is developing a range of robots that mimic wildlife adapted for all environments on Earth for military warfare.

Liz O'Sullivan says she struggled for months as she learned more about the military project her in which her employer, Clarifai, was participating. Liz O'Sullivan says she struggled for months as she learned more about the military project her in which her employer, Clarifai, was participating. On the night of Jan. 16, Liz O'Sullivan sent a letter she'd been working on for weeks. It was directed at her boss, Matt Zeiler, the founder and CEO of Clarifai, a tech company. "The moment before I hit send and then afterwards, my heart, I could just feel it racing," she says.