Probabilistic generative models can be used for compression, denoising, inpainting, texture synthesis, semi-supervised learning, unsupervised feature learning, and other tasks. Given this wide range of applications, it is not surprising that a lot of heterogeneity exists in the way these models are formulated, trained, and evaluated. As a consequence, direct comparison between models is often difficult. This article reviews mostly known but often underappreciated properties relating to the evaluation and interpretation of generative models with a focus on image models. In particular, we show that three of the currently most commonly used criteria---average log-likelihood, Parzen window estimates, and visual fidelity of samples---are largely independent of each other when the data is high-dimensional. Good performance with respect to one criterion therefore need not imply good performance with respect to the other criteria. Our results show that extrapolation from one criterion to another is not warranted and generative models need to be evaluated directly with respect to the application(s) they were intended for. In addition, we provide examples demonstrating that Parzen window estimates should generally be avoided.

One key buzzword these days is "algorithm," which technically means any computational formula but which has come to mean a formula that predicts our behavior. Amazon and Netflix have algorithms that predict what books a user is likely to want to read or what movies and TV shows he or she is likely to want to watch. Facebook has an algorithm that predicts the news a user is likely to want. Dating sites like Match.com and OkCupid use algorithms to predict with whom we would fall in love. Google, with the most famous algorithm of all, predicts what we want when we type a search term.

It's hard to find someone who isn't a fan of "Game of Thrones." The TV show, which returns Sunday, has reached peaks of popularity that few shows do, and draws in fans of all shapes and sizes -- even computers. Maluuba, a Canadian startup, posted a YouTube video on Friday showing its artificial-intelligence software reading the synopsis for the fifth season of "Game of Thrones'" and immediately knowing all of the show's plot lines. It's the equivalent to a human, let's call him "John" for this example, who knows nothing about the show, has never seen it, takes one look at a Wikipedia page and instantaneously knows everything that's happening. "Who stabbed Jon Snow?" the Maluuba engineer asks the AI software.

As the average age of farmers globally creeps higher and retirement looms, Japan has a solution: robots and driver-less tractors. The Group-of-Seven agriculture ministers meet in Japan's northern prefecture of Niigata this weekend for the first time in seven years to discuss how to meet increasing food demand as aging farmers retire without successors. With the average age of Japanese farmers now 67, Agriculture Minister Hiroshi Moriyama will outline his idea of replacing retiring growers with Japanese-developed autonomous tractors and backpack-carried robots. U.S. Agriculture Secretary Tom Vilsack has warned that left unchecked, aging farmers could threaten the ability to produce the food the world needs. The average age of growers in developed countries is now about 60, according to the United Nations.

We have produced a 90-second video (click on this link to view the video) showing a'random walk' (a particular case of a Markov process) evolving over 400,000 steps. Figure 1 below shows the last frame (out of 2,000 frames, each one with 200 new steps). The video consists of 2000 frames, each showing 200 new steps (represented by red dots), as the random walk progresses over time. Sometimes we seem to get stuck locally, sometimes we are dramatically progressing at high speed. Older frames still stay on the video, but are shown in gray rather than red.

A data scientist is one of the most in-demand, high-profile careers in IT today, but Tom Walsh and Alex Krowitz have been working behind the scenes in the field for years. Walsh, a research engineer and Krowitz, a senior research engineer at cloud workforce management solutions company Kronos, sift through the influx of proprietary and customer data to identify patterns and gain insights based on that data. There are generally two kinds of projects we regularly handle; mining patterns within data to improve our own products is one and the other is taking on specific sets of customer data to gather and deliver insights from that," says Walsh. What companies are looking for is ultimately the capability to make predictions based on that data, says Krowitz. Companies use those predictions to help drive everything from marketing strategy to resource allocation, personnel levels and staffing, or to predict retail sales, he says. "We have products that use machine learning algorithms to help customers with these predictions.

Big data can't deliver on its potential unless enterprises have the right tools to extract insights. Woodside, an Australia-based oil and gas giant, realizes this and is using advanced machine learning technology to leverage its data via predictive analysis. Front and center in the company's toolkit is IBM Watson, a cutting-edge machine learning and natural language processing platform that analyzes vast amounts of unstructured data. According to CIO, Woodside is using a variety of big data tools -- including Amazon Web Services (AWS), Apache Spark and Watson -- to improve operational efficiency and predict potential catastrophes at its production facilities. Elsa Jordan, principal data scientist at Woodside, told attendees of the Chief Analytics Officer Forum in Sydney how the company has implemented these data science technologies in recent years and how the Watson engine has become a key component of the organization's big data platform.

A former science teacher who believed in the power and possibility of online learning over two decades ago, he taught himself how to build courses in HTML on class intranets. Kevin taught one of the first hybrid, educational technology courses for teachers, for the University of Washington. And, after building countless web pages and classes on the early world wide web, he now helps develop e-learning programs, consults on virtual training'best practices' and has many interests in other internet and educational technology-related areas. Kevin finds he's now enjoying learning more from his children who are all deep into their own technology-related careers and entrepreneurial endeavors. With two new grandchildren, he's investigating more seriously the advancing new technologies in an effort to understand the knowledge and skills necessary to achieve happiness and success in a technological future.

A trip to Iceland wouldn't be complete without a dip in the Blue Lagoon, a man-made geothermal pool on Reykjanes peninsula. A trip to Iceland wouldn't be complete without a dip in the Blue Lagoon, a man-made geothermal pool on Reykjanes peninsula. The premise is simple: Correspondents, editors and producers from our newsroom share the pieces that have kept them reading, using the #NPRreads hashtag. Each weekend, we highlight some of the best stories. You have storms, you have darkness, but the pool is a place to find yourself again.

Peter Singer is a professor of bioethics at Princeton University and Laureate Professor at the University of Melbourne His books include Animal Liberation, The Life You Can Save, The Most Good You Can Do, and, most recently, Famine, Affluence and Morality. Last month, AlphaGo, a computer program specially designed to play the game Go, caused shock waves among aficionados when it defeated Lee Sedol, one of the world's top-ranked professional players, winning a five-game tournament by a score of 4-1. Why, you may ask, is that news? Twenty years have passed since the IBM computer Deep Blue defeated world chess champion Garry Kasparov and we all know computers have improved since then. But Deep Blue won through sheer computing power, using its ability to calculate the outcomes of more moves to a deeper level than even a world champion can.