Image captioning models are becoming increasingly successful at describing the content of images in restricted domains. However, if these models are to function in the wild --- for example, as assistants for people with impaired vision --- a much larger number and variety of visual concepts must be understood. To address this problem, we teach image captioning models new visual concepts from labeled images and object detection datasets. Since image labels and object classes can be interpreted as partial captions, we formulate this problem as learning from partially-specified sequence data. We then propose a novel algorithm for training sequence models, such as recurrent neural networks, on partially-specified sequences which we represent using finite state automata. In the context of image captioning, our method lifts the restriction that previously required image captioning models to be trained on paired image-sentence corpora only, or otherwise required specialized model architectures to take advantage of alternative data modalities. Applying our approach to an existing neural captioning model, we achieve state of the art results on the novel object captioning task using the COCO dataset. We further show that we can train a captioning model to describe new visual concepts from the Open Images dataset while maintaining competitive COCO evaluation scores.

Knowledge bases (KB), both automatically and manually constructed, are often incomplete --- many valid facts can be inferred from the KB by synthesizing existing information. A popular approach to KB completion is to infer new relations by combinatory reasoning over the information found along other paths connecting a pair of entities. Given the enormous size of KBs and the exponential number of paths, previous path-based models have considered only the problem of predicting a missing relation given two entities or evaluating the truth of a proposed triple. Additionally, these methods have traditionally used random paths between fixed entity pairs or more recently learned to pick paths between them. We propose a new algorithm MINERVA, which addresses the much more difficult and practical task of answering questions where the relation is known, but only one entity. Since random walks are impractical in a setting with combinatorially many destinations from a start node, we present a neural reinforcement learning approach which learns how to navigate the graph conditioned on the input query to find predictive paths. Empirically, this approach obtains state-of-the-art results on several datasets, significantly outperforming prior methods.

Biased AI can have serious life-altering consequences for individuals. It was reported in 2016 that the COMPAS program -- or Correctional Offender Management Profiling for Alternative Sanctions -- used by U.S. judges in some states to help decide parole and other sentencing conditions, had racial biases. "COMPAS uses machine learning and historical data to predict the probability that a violent criminal will re-offend. Unfortunately it incorrectly predicts black people are more likely to re-offend than they do," according to a paper by Toby Walsh, an artificial intelligence professor at the University of New South Wales. While biases in AI exist, it is important that certain decisions are not left to software, Walsh told CNBC.

Mining corporation Rio Tinto says that an autonomous rail system called AutoHaul that it's been developing in the remote Pilbara region of Australia for several years is now entirely operational -- an accomplishment the company says makes the system the "world's largest robot." "It's been a challenging journey to automate a rail network of this size and scale in a remote location like the Pilbara," Rio Tinto's managing director Ivan Vella told the Sidney Morning Herald, "but early results indicate significant potential to improve productivity, providing increased system flexibility and reducing bottlenecks." The ore-hauling train is just one part of an ambitious automation project involving robotics and driverless vehicles that Rio Tinto wants to use to automate its mining operations. The company conducted its first test of the train without a human on board earlier this year, and it now claims that the system has completed more than a million kilometers (620,000 miles) of autonomous travel. In response to concerns from labor unions, Rio Tinto promised that the autonomous rail system will not eliminate any existing jobs in the coming year -- though it's difficult to imagine the project won't cut into human jobs in the long term.

Negative user preference is an important context that is not sufficiently utilized by many existing recommender systems. This context is especially useful in scenarios where the cost of negative items is high for the users. In this work, we describe a new recommender algorithm that explicitly models negative user preferences in order to recommend more positive items at the top of recommendation-lists. We build upon existing machine-learning model to incorporate the contextual information provided by negative user preference. With experimental evaluations on two openly available datasets, we show that our method is able to improve recommendation quality: by improving accuracy and at the same time reducing the number of negative items at the top of recommendation-lists. Our work demonstrates the value of the contextual information provided by negative feedback, and can also be extended to signed social networks and link prediction in other networks.

Data mining is a computational process of finding patterns in large data sets with methods like artificial intelligence, machine learning, statistics, analysis, and systems. With a goal to get information from that data that can later be used. The relationship between customers and companies has changed – companies have become easily accessible through social media and messaging platforms which provide valuable but unstructured data. This is why companies need data mining and tools that come with it. Data mining tools allow businesses to gather information from these platforms and use it for their purposes – namely, marketing evaluation and analysis.

In less than 50 years, Artificial Intelligence (AI) will match humans traits like adaptability, creativity and emotional intelligence, an expert has predicted. Speaking at the "Festival of Dangerous Ideas" at University of New South Wales in Sydney on Sunday, Professor Toby Walsh said AI will match human intelligence by 2062, media reported on Monday "Toby Walsh, Scientia Professor of Artificial Intelligence at UNSW Sydney, has put a date on this looming reality. "He considers 2062 the year that artificial intelligence will match human intelligence, although a fundamental shift has already occurred in the world as we know it," the university said in a statement. Walsh argued that we are already experiencing the risks of AI that seem to be so far in the future. "Even without machines that are very smart, I'm starting to get a little bit nervous about where it's going and the important choices we should be making", said Walsh who has written a book "2062: The World that AI Made".

Drones could someday revolutionize e-commerce by cutting delivery times, reducing energy use and lowering costs. For now, they are dividing neighbors in the suburban neighborhood of Bonython, where one of the world's most advanced drone-delivery tests has taken flight. Tech companies are tinkering with drone deliveries all over the world. Wing is a step ahead of some by routinely bringing everyday items to customers in an entire neighborhood. Residents can use a smartphone app to order food, hardware supplies and over-the-counter medications from half a dozen retailers.

Emergent and unscheduled cardiology admissions from cardiac catheterization laboratory add complexity to the management of Cardiology and in-patient department. In this article, we sought to study the behavior of cardiology admissions from Catheterization laboratory using time series models. Our research involves retrospective cardiology admission data from March 1, 2012, to November 3, 2016, retrieved from a hospital in Iowa. Autoregressive integrated moving average (ARIMA), Holts method, mean method, na\"ive method, seasonal na\"ive, exponential smoothing, and drift method were implemented to forecast weekly cardiology admissions from Catheterization laboratory. ARIMA (2,0,2) (1,1,1) was selected as the best fit model with the minimum sum of error, Akaike information criterion and Schwartz Bayesian criterion. The model failed to reject the null hypothesis of stationarity, it lacked the evidence of independence, and rejected the null hypothesis of normality. The implication of this study will not only improve catheterization laboratory staff schedule, advocate efficient use of imaging equipment and inpatient telemetry beds but also equip management to proactively tackle inpatient overcrowding, plan for physical capacity expansion and so forth.

Honey has been collected and used by humankind as both a food and medicine for thousands of years. However, in the modern economy, honey has become subject to mislabelling and adulteration making it the third most faked food product in the world. The international scale of fraudulent honey has had both economic and environmental ramifications. In this paper, we propose a novel method of identifying fraudulent honey using machine learning augmented microscopy.