Machine learning is currently dominated by largely experimental work focused on improvements in a few key tasks. However, the impressive accuracy numbers of the best performing models are questionable because the same test sets have been used to select these models for multiple years now. To understand the danger of overfitting, we measure the accuracy of CIFAR-10 classifiers by creating a new test set of truly unseen images. Although we ensure that the new test set is as close to the original data distribution as possible, we find a large drop in accuracy (4% to 10%) for a broad range of deep learning models. Yet more recent models with higher original accuracy show a smaller drop and better overall performance, indicating that this drop is likely not due to overfitting based on adaptivity. Instead, we view our results as evidence that current accuracy numbers are brittle and susceptible to even minute natural variations in the data distribution.

Once upon a time Elon Musk was our era's real-life Tony Stark, a billionaire Iron Man streaking across the sky with technology to save the planet and take us to Mars. Reusable rockets, electric cars, solar power, he did them all, taking time out to advise Robert Downey Jr on how to play the Marvel superhero on a trajectory seemingly forever up, up, up. Now Musk, 46, is literally and figuratively in a long, dark hole. He is tunneling beneath Los Angeles to create a prototype underground transit network which, he says, can save the city from traffic congestion. But a recently released video of the tunnel plus a map of potential lines coincided with a dark turn in Musk's fortunes and reputation, creating the impression of a man in a labyrinth of his own making.

An attacker just needs to play ultrasonic sounds through a built-in speaker of a target computer or by using a speaker in its proximity. The principle is simple, the technique leverages specially crafted acoustic signals to cause significant vibrations in the HDDs components that could cause severe damage. Modern HDDs use shock sensors to prevent the head crash, but the team of researchers has demonstrated that sonic and ultrasonic sounds could cause false positives in the shock sensor, causing a drive to park the head in a wrong position. "We created and modeled a new feedback controller that could be deployed as a firmware update to attenuate the intentional acoustic interference. Our sensor fusion method prevents unnecessary head parking by detecting ultrasonic triggering of the shock sensor" reads the paper published by the experts.

Is Facebook pumping up the volume on what AI can mean to the future of music? You can decide after having a look at what Facebook AI Research scientists have been up to. A number of sites including The Next Web have reported that they unveiled a neural network capable of translating music from one style, genre, and set of instruments to another. You can check out their paper, "A Universal Music Translation Network" by authors Noam Mor, Lior Wolf, Adam Polyak, Yaniv Taigman, Facebook AI Research. The paper is on arXiv.

The influence of Artificial Intelligence (AI) and Artificial Life (ALife) technologies upon society, and their potential to fundamentally shape the future evolution of humankind, are topics very much at the forefront of current scientific, governmental and public debate. While these might seem like very modern concerns, they have a long history that is often disregarded in contemporary discourse. Insofar as current debates do acknowledge the history of these ideas, they rarely look back further than the origin of the modern digital computer age in the 1940s-50s. In this paper we explore the earlier history of these concepts. We focus in particular on the idea of self-reproducing and evolving machines, and potential implications for our own species. We show that discussion of these topics arose in the 1860s, within a decade of the publication of Darwin's The Origin of Species, and attracted increasing interest from scientists, novelists and the general public in the early 1900s. After introducing the relevant work from this period, we categorise the various visions presented by these authors of the future implications of evolving machines for humanity. We suggest that current debates on the co-evolution of society and technology can be enriched by a proper appreciation of the long history of the ideas involved.

Intelligent systems for the annotation of media content are increasingly being used for the automation of parts of social science research. In this domain the problem of integrating various Artificial Intelligence (AI) algorithms into a single intelligent system arises spontaneously. As part of our ongoing effort in automating media content analysis for the social sciences, we have built a modular system by combining multiple AI modules into a flexible framework in which they can cooperate in complex tasks. Our system combines data gathering, machine translation, topic classification, extraction and annotation of entities and social networks, as well as many other tasks that have been perfected over the past years of AI research. Over the last few years, it has allowed us to realise a series of scientific studies over a vast range of applications including comparative studies between news outlets and media content in different countries, modelling of user preferences, and monitoring public mood. The framework is flexible and allows the design and implementation of modular agents, where simple modules cooperate in the annotation of a large dataset without central coordination.

There are tons of neural style transfer papers that came out over the past years, so there are a lot of different repos implementing them. Which one do you think works the best? That would be for some HD pictures containing people.

Just like they do every week, the Season 4, Week 6 challenges have leaked online, courtesy of the dataminers at Fortnite Tracker. We're more than halfway through the season now, and many players are closing in on the ultimate goals of the season: for some that might mean unlocking and upgrading the Omega skin, which requires Battle Pass Tier 100 and Season Level 80. For others, that might mean unlocking the Blockbuster skin, which requires finishing seven complete weeks of challenges. Whatever you're working towards, the weekly challenges are your best source of Battle Pass tiers and experience, so let's take a look at what we've got. Take note that these are subject to change, and have done so in the past: last week one of the collection challenges wound up replaced by the charming disco ball dance challenge.

Starting with the idea that sentiment analysis models should be able to predict not only positive or negative but also other psychological states of a person, we implement a sentiment analysis model to investigate the relationship between the model and emotional state. We first examine psychological measurements of 64 participants and ask them to write a book report about a story. After that, we train our sentiment analysis model using crawled movie review data. We finally evaluate participants' writings, using the pretrained model as a concept of transfer learning. The result shows that sentiment analysis model performs good at predicting a score, but the score does not have any correlation with human's self-checked sentiment.

In many practical problems, a learning agent may want to learn the best action in hindsight without ever taking a bad action, which is significantly worse than the default production action. In general, this is impossible because the agent has to explore unknown actions, some of which can be bad, to learn better actions. However, when the actions are combinatorial, this may be possible if the unknown action can be evaluated by interleaving it with the production action. We formalize this concept as learning in stochastic combinatorial semi-bandits with exchangeable actions. We design efficient learning algorithms for this problem, bound their n-step regret, and evaluate them on both synthetic and real-world problems. Our real-world experiments show that our algorithms can learn to recommend K most attractive movies without ever violating a strict production constraint, both overall and subject to a diversity constraint.