The field of Multi-Agent System (MAS) is an active area of research within Artificial Intelligence, with an increasingly important impact in industrial and other real-world applications. Within a MAS, autonomous agents interact to pursue personal interests and/or to achieve common objectives. Distributed Constraint Optimization Problems (DCOPs) have emerged as one of the prominent agent architectures to govern the agents' autonomous behavior, where both algorithms and communication models are driven by the structure of the specific problem. During the last decade, several extensions to the DCOP model have enabled them to support MAS in complex, real-time, and uncertain environments. This survey aims at providing an overview of the DCOP model, giving a classification of its multiple extensions and addressing both resolution methods and applications that find a natural mapping within each class of DCOPs. The proposed classification suggests several future perspectives for DCOP extensions, and identifies challenges in the design of efficient resolution algorithms, possibly through the adaptation of strategies from different areas.

As machine learning algorithms are increasingly applied to high impact yet high risk tasks, such as medical diagnosis or autonomous driving, it is critical that researchers can explain how such algorithms arrived at their predictions. In recent years, a number of image saliency methods have been developed to summarize where highly complex neural networks "look" in an image for evidence for their predictions. However, these techniques are limited by their heuristic nature and architectural constraints. In this paper, we make two main contributions: First, we propose a general framework for learning different kinds of explanations for any black box algorithm. Second, we specialise the framework to find the part of an image most responsible for a classifier decision. Unlike previous works, our method is model-agnostic and testable because it is grounded in explicit and interpretable image perturbations.

Mutation is one of the most important stages of genetic algorithms because of its impact on the exploration of the search space, and in overcoming premature convergence. Since there are many types of mutations one common problem lies in selecting the appropriate type. The decision then becomes more difficult and needs more trial and error to find the best mutation to be used. This paper investigates the use of more than one mutation operator to enhance the performance of genetic algorithms. New mutation operators are proposed, in addition to two election strategies for the mutation operators. One is based on selecting the best mutation operator and the other randomly selects any operator. Several experiments were conducted on the Travelling Salesman Problem (TSP) to evaluate the proposed methods. These were compared to the well-known exchange mutation and rearrangement mutation. The results show the importance of some of the proposed methods, in addition to the significant enhancement of the genetic algorithms' performance, particularly when using more than one mutation operator.

The Justice Department will soon start trying to jam cellphones smuggled into federal prisons and used for criminal activity, part of a broader safety initiative that is also focused on preventing drones from airdropping contraband to inmates. Deputy Attorney General Rod J. Rosenstein told the American Correctional Association's conference in Orlando on Monday that, while the law prohibits cellphone use by federal inmates, the Bureau of Prisons confiscated 5,116 such phones in 2016, and preliminary numbers for 2017 indicate a 28 percent increase. "That is a major safety issue," he said in his speech. "Cellphones are used to run criminal enterprises, facilitate the commission of violent crimes and thwart law enforcement." When he was the U.S. attorney in Maryland, Rosenstein prosecuted an inmate who used a smuggled cellphone to order the murder of a witness.

To perform tasks specified by natural language instructions, autonomous agents need to extract semantically meaningful representations of language and map it to visual elements and actions in the environment. This problem is called task-oriented language grounding. We propose an end-to-end trainable neural architecture for task-oriented language grounding in 3D environments which assumes no prior linguistic or perceptual knowledge and requires only raw pixels from the environment and the natural language instruction as input. The proposed model combines the image and text representations using a Gated-Attention mechanism and learns a policy to execute the natural language instruction using standard reinforcement and imitation learning methods. We show the effectiveness of the proposed model on unseen instructions as well as unseen maps, both quantitatively and qualitatively. We also introduce a novel environment based on a 3D game engine to simulate the challenges of task-oriented language grounding over a rich set of instructions and environment states.

Knowledge graph embedding aims to embed entities and relations of knowledge graphs into low-dimensional vector spaces. Translating embedding methods regard relations as the translation from head entities to tail entities, which achieve the state-of-the-art results among knowledge graph embedding methods. However, a major limitation of these methods is the time consuming training process, which may take several days or even weeks for large knowledge graphs, and result in great difficulty in practical applications. In this paper, we propose an efficient parallel framework for translating embedding methods, called ParTrans-X, which enables the methods to be paralleled without locks by utilizing the distinguished structures of knowledge graphs. Experiments on two datasets with three typical translating embedding methods, i.e., TransE [3], TransH [17], and a more efficient variant TransE- AdaGrad [10] validate that ParTrans-X can speed up the training process by more than an order of magnitude.

Ever since software development progressed from compiler code, there have existed a range of tools to help make developing easier and more effective. A number of projects point in an interesting direction for the sector however. For instance, Amazon recently announced the launch of Cloud 9, an integrated development environment that directly connects to the cloud computing platform provided by the company. It's a strong sign that machine learning is becoming a strong presence in software development on the cloud. Developers using the platform can easily tap into the cloud-based AI baked into the software to create the next generation of apps. Amazon hope that it will allow more of the software we use every day to have intelligence built in as standard.

The battle now raging between the big technology companies for consumer cash is focused on the voice-controlled smart speaker. Having already conquered the pocket with the ubiquitous smartphone, big tech has been struggling to come up with the next must-have gadget that will open up a potentially lucrative new market – the home. A pilot light was lit when Amazon's Echo launched in 2014 and became a sleeper hit. Now the voice controlled smart speaker is rapidly becoming the next big thing, capable of answering questions, setting timers, playing music, controlling other devices about the home, or even potentially selling products. "The last 12 months have been explosive for smart speakers, which have surged into the mass market for two reasons.

With the dawn of the age of Data Science, there is an increased interest in learning and applying algorithms, not just by business analysts or data scientists, but by several other professionals whose core job may not be crunching data or building models. Good sign, indeed, if one understands the when, why and how of applying these fantastic techniques. If your scatterplot shows curvilinear relationship, keep in mind that higher order polynomials (2 or above) may do a better job at modelling the data. Compare models, statistics and decide for yourself which model best explains your data. For validity of a LR model, the VIF (Variance Inflationary Factor) should not be too high. How high is too high?

The technology is expected to wipe out millions of jobs, but surprisingly create many more by 2020. Over two million jobs could be created by artificial intelligence (AI) by 2020, outnumbering the number of jobs lost to the technology, according to Gartner. In a recent report, Gartner revealed that by 2020 AI is expected to create a total of 2.3 million jobs, but destroy 1.8 million jobs. Though the latter is a significant amount, in the long term more jobs can be created and enhanced by the technology across the job ladder, according to the analyst firm. AI implementation will affect every industry, with manufacturing expected to be hit the hardest by the technology.