Multiple instance learning (MIL) is a form of weakly supervised learning where training instances are arranged in sets, called bags, and a label is provided for the entire bag. This formulation is gaining interest because it naturally fits various problems and allows to leverage weakly labeled data. Consequently, it has been used in diverse application fields such as computer vision and document classification. However, learning from bags raises important challenges that are unique to MIL. This paper provides a comprehensive survey of the characteristics which define and differentiate the types of MIL problems. Until now, these problem characteristics have not been formally identified and described. As a result, the variations in performance of MIL algorithms from one data set to another are difficult to explain. In this paper, MIL problem characteristics are grouped into four broad categories: the composition of the bags, the types of data distribution, the ambiguity of instance labels, and the task to be performed. Methods specialized to address each category are reviewed. Then, the extent to which these characteristics manifest themselves in key MIL application areas are described. Finally, experiments are conducted to compare the performance of 16 state-of-the-art MIL methods on selected problem characteristics. This paper provides insight on how the problem characteristics affect MIL algorithms, recommendations for future benchmarking and promising avenues for research.

Does every painter leave a fingerprint? Accurately distinguishing the artwork of a master from a forgery can mean a difference in millions of dollars. In the Painter by Numbers playground competition hosted by Kiri Nichol (AKA small yellow duck), Kagglers were challenged to identify whether pairs of paintings were created by the same artist. In this winner's interview, Nejc Ilenič takes us through his first place solution to this painter recognition challenge. His combination of unsupervised and supervised learning methods helped him achieve a final AUC of 0.9289.

Bottom line: Machine learning is providing the needed algorithms, applications, and frameworks to bring greater predictive accuracy and value to enterprises' data, leading to diverse company-wide strategies succeeding faster and more profitably than before. The good news for businesses is that all the data they have been saving for years can now be turned into a competitive advantage and lead to strategic goals being accomplished. Revenue teams are using machine learning to optimize promotions, compensation and rebates drive the desired behavior across selling channels. Predicting propensity to buy across all channels, making personalized recommendations to customers, forecasting long-term customer loyalty and anticipating potential credit risks of suppliers and buyers are Figure 1 provides an overview of machine learning applications by industry. Unlike advanced analytics techniques that seek out causality first, machine learning techniques are designed to seek out opportunities to optimize decisions based on the predictive value of large-scale data sets.

I f anyone can calm fears of a robot apocalypse, it's Kevin Kelly. Over the years -- first as the founding executive editor of Wired, then as the author of books like What Technology Wants and Out of Control: The New Biology of Machines, Social Systems and the Economic World -- he has become one of the 21st century's most prescient theorists not only on the future of technology but also on our constantly evolving relationship with it. In his latest book, The Inevitable: Understanding the 12 Technological Forces that Will Shape Our Future, Kelly writes about the unstoppable trends that we often fear when it comes to technological progress. In a recent interview with Slack, he laid out his vision of the future of work and some simple reasons why we may want to reconsider some of our deep-rooted anxieties about it. Why do you think there's such a huge amount of fear around automation and AI?

Friday is here, and we learned that Magic Leap's wondrous demo video last year was all CGI magic, that scientists have discovered a dinosaur tail with feathers, and explain why Pebble fans might not be happy with the company's new owners. For the last couple of years, Magic Leap has been promising a groundbreaking augmented reality experience. Despite hiring hundreds of employees and snagging big-name financial backers (like Google) it hasn't actually shown off the technology publicly, leaving all of us to wonder what's going on. The Information reports that the company has had trouble implementing some of its patented fiber-optic technology, and may be preparing a wearable headset that's closer to what we've seen from Microsoft's HoloLens than the WETA-created demo video it posted last year. On Thursday John Glenn died at the age of 95 in Columbus, Ohio.

This feature could be used to provide an overview of a recently enacted financial services regulation or a news event.

The following interview is part of our ongoing Expert Series that asks C-level professionals, team presidents, league executives, athletic directors and other sports influencers about their latest thoughts and insights on new technologies impacting the sports industry. Jody Mulkey is the Chief Technology Officer at Ticketmaster. An accomplished technologist and inspirational engineering leader, he is known for building high performance systems and teams. Prior to Ticketmaster, the Texas native spent over 14 years at Shopzilla Inc, a leading source for connecting buyers and sellers online that reaches a global audience of over 40 million shoppers monthly. As Chief Information Officer of Shopzilla, he led the overall the technology development and operations of the company.

In recent years, advanced machine learning techniques have enabled computers to recognize objects in images, understand commands from spoken sentences, and translate written language. But while consumer products like Apple's Siri and Google Translate might operate in real time, actually building the complex mathematical models these tools rely on can take traditional computers large amounts of time, energy, and processing power. As a result, chipmakers like Intel, graphics powerhouse Nvidia, mobile computing kingpin Qualcomm, and a number of startups are racing to develop specialized hardware to make modern deep learning significantly cheaper and faster. The importance of such chips for developing and training new AI algorithms quickly cannot be understated, according to some AI researchers. "Instead of months, it could be days," Nvidia CEO Jen-Hsun Huang said in a November earnings call, discussing the time required to train a computer to do a new task.

SAN FRANCISCO – Forget the Terminator. The next robot on the horizon may be wearing a lab coat. Artificial intelligence (AI) is already helping scientists form testable hypotheses that enable experts to run real experiments, and the technology may soon be poised to help businesses make decisions, one scientist says. However, that doesn't mean the machines will be taking over from humans entirely. Instead, humans and machines have complementary skillsets, so AI could help researchers with the work they already do, Laura Haas, a computer scientist and director of the IBM Research Accelerated Discovery Lab in San Jose, California, said here Wednesday (Dec.

MIT researchers have designed a new machine-learning system that can learn by itself to extract text information for statistical analysis when available data is scarce. This new "information extraction" system turns machine learning on its head. It works like humans do. When we run out of data in a study (say, differentiating between fake and real news), we simply search the Internet for more data, and then we piece the new data together to make sense out of it all. That differs from most machine-learning systems, which are fed as many training examples as possible to increase the chances that the system will be able to handle difficult problems by looking for patterns compared to training data.