State of the art algorithms for many pattern recognition problems rely on deep network models. Training these models requires a large labeled dataset and considerable computational resources. Also, it is difficult to understand the working of these learned models, limiting their use in some critical applications. Towards addressing these limitations, our architecture draws inspiration from research in cognitive systems, and integrates the principles of commonsense logical reasoning, inductive learning, and deep learning. In the context of answering explanatory questions about scenes and the underlying classification problems, the architecture uses deep networks for extracting features from images and for generating answers to queries. Between these deep networks, it embeds components for non-monotonic logical reasoning with incomplete commonsense domain knowledge, and for decision tree induction. It also incrementally learns and reasons with previously unknown constraints governing the domain's states. We evaluated the architecture in the context of datasets of simulated and real-world images, and a simulated robot computing, executing, and providing explanatory descriptions of plans. Experimental results indicate that in comparison with an ``end to end'' architecture of deep networks, our architecture provides better accuracy on classification problems when the training dataset is small, comparable accuracy with larger datasets, and more accurate answers to explanatory questions. Furthermore, incremental acquisition of previously unknown constraints improves the ability to answer explanatory questions, and extending non-monotonic logical reasoning to support planning and diagnostics improves the reliability and efficiency of computing and executing plans on a simulated robot.

This work focuses on studying players behaviour in interactive narratives with the aim to simulate their choices. Besides sub-optimal player behaviour due to limited knowledge about the environment, the difference in each player's style and preferences represents a challenge when trying to make an intelligent system mimic their actions. Based on observations from players interactions with an extract from the interactive fiction Anchorhead, we created a player profile to guide the behaviour of a generic player model based on the BDI (Belief-Desire-Intention) model of agency. We evaluated our approach using qualitative and quantitative methods and found that the player profile can improve the performance of the BDI player model. However, we found that players self-assessment did not yield accurate data to populate their player profile under our current approach.

In this paper, we present a new modality for intelligent inte r-active narratives within the theatre domain. We discuss the possibilities of using an intelligent agent that serves as a drama manager a nd as an actor that plays a character within the live theatre exper ience. We pose a set of research challenges that arise from our analysi s towards the implementation of such an agent, as well as potential method ologies as a starting point to bridge the gaps between current literatu re and the proposed modality.

Neural dialogue models have been widely adopted in various chatbot applications because of their good performance in simulating and generalizing human conversations. However, there exists a dark side of these models -- due to the vulnerability of neural networks, a neural dialogue model can be manipulated by users to say what they want, which brings in concerns about the security of practical chatbot services. In this work, we investigate whether we can craft inputs that lead a well-trained black-box neural dialogue model to generate targeted outputs. We formulate this as a reinforcement learning (RL) problem and train a Reverse Dialogue Generator which efficiently finds such inputs for targeted outputs. Experiments conducted on a representative neural dialogue model show that our proposed model is able to discover such desired inputs in a considerable portion of cases. Overall, our work reveals this weakness of neural dialogue models and may prompt further researches of developing corresponding solutions to avoid it.

Horticulture NZ's conference for 2019 was held over two days at Mystery Creek in Hamilton from 31 July, under the theme of'Our Food Future'. Mark attended on behalf of PlantTech and contributed to the discussion about the emerging use of technology in horticulture and how the widespread application of drones, robotics and advancing imaging would become easier and more affordable over time. The pace of change has been described as being similar to the principle of Moore's Law, which states that the speed and capability of computers can be expected to double every 18 months. It would appear that these developing technologies are on a very similar trajectory. With the increasing demand for food, there's a great deal of interest in how the industry can respond to that challenge without creating further pressure on the environment.

Top Stories, Tweets Top Stories, Aug 5-11: Knowing Your Neighbours: Machine Learning on Graphs; What is Benford's Law and why is it important for data science? Top KDnuggets tweets, Jul 31 - Aug 06: NLP vs. NLU: from Understanding a Language to Its Processing News Exploratory Data Analysis Using Python Meetings The slow, startling triumph of Reverend Bayes - John Elder's 2019 Keynote at PAW in London Cambridge Analytica whistleblower Chris Wylie to headline Big Data LDN 2019 keynote programme Academic Postdoctoral position (2 years) in multivariate analysis and deep learning PhD student position in computational science with focus on chemistry Monash University: Research Fellow - Computer Vision [Melbourne, Australia] Image of the week 12 NLP Researchers, Practitioners, Innovators to Follow Learn how to do Machine Learning on Graphs; Follow these 12 amazing leaders in NLP; Read the explanation of Deep Learning for NLP, including ANNs, RNNs and LSTMs; Understand what is Benford's Law and why is it important for data science; Find the 6 key concepts in Andrew NG Machine Learning Yearning; and more. Knowing Your Neighbours: Machine Learning on Graphs 12 NLP Researchers, Practitioners & Innovators You Should Be Following Deep Learning for NLP: ANNs, RNNs and LSTMs explained! What is Benford's Law and why is it important for data science?

The demand for artificial intelligence has grown significantly in the last few years due to the advantages it provides. Rising use of big data, growing demand for greater transparency and visibility into supply chain data and processes, and increasing adoption of AI for improving consumer services and satisfaction are some of the other factors driving the demand in this market. Moreover, growing applicability of AI in various industries has further augmented the demand in this market. The global artificial intelligence in supply chain market could be classified on basis of technology, application, end-user industry, and offerings. The end-user industry category can further be segmented into manufacturing, aerospace, automotive, retail, consumer packaged goods, healthcare, food and beverages, and others.

Almost two years ago, Dennis Degray sent an unusual text message to his friend. "You are holding in your hand the very first text message ever sent from the neurons of one mind to the mobile device of another," he recalls it read. Degray, 66, has been paralysed from the collarbones down since an unlucky fall over a decade ago. He was able to send the message because in 2016 he had two tiny squares of silicon with protruding metal electrodes surgically implanted in his motor cortex, the part of the brain that controls movement. By imagining moving a joystick with his hand, he is able to move a cursor to select letters on a screen.

Countless studies have shown not only that gender bias is real but also that it has significant repercussions. The pattern of diminishing representation on the higher rungs of the career ladder in STEM fields also holds true broadly in the corporate world: 56% of university graduates are women, yet women represent only 38% of the total workforce, 26% of the managerial ranks, 15% of executive-level positions, and 5% of the CEO ranks. How, then, will AI affect gender diversity in the leadership pipeline? AI has the potential to mitigate the corporate gender and leadership gaps by removing bias in recruiting, evaluation, and promotion decisions; by helping improve retention of women employees; and, potentially, by intervening in the everyday interactions that affect employees' sense of inclusion. Biased data is a source of risk.

The Internet of things (IoT) is the inter-networking of physical devices (also termed as connected devices or smart devices), vehicles, buildings and other objects (which could be smart wearable, diagnostic device, kitchen appliances etc.) embedded with electronics, software, sensors, actuators, and network connectivity that enables these "smart objects" to collect and exchange data. In other words, Internet of things is a global infrastructure for the information society. IoT allows advanced services by interconnecting (physical and virtual) things based on existing and evolving interoperable information and communication technologies. For example, the smart refrigerator in your kitchen (at home) can send you an alert (or notification) on your smartphone (while you are leaving office) when you're out of milk or gas. Your wearable or smartwatch can warn you if there is something wrong with your pulse or heart-rate. Additionally, all this information gets recorded. Later, the software after looking at the data can provide you information like: you are likely to run of milk on Wednesday, run out of gas in two weeks, or likely to get a heart attack in three months (so, time for a check-up and take precautions).