Clustering is a widely used unsupervised learning method for finding structure in the data. However, the resulting clusters are typically presented without any guarantees on their robustness; slightly changing the used data sample or re-running a clustering algorithm involving some stochastic component may lead to completely different clusters. There is, hence, a need for techniques that can quantify the instability of the generated clusters. In this study, we propose a technique for quantifying the instability of a clustering solution and for finding robust clusters, termed core clusters, which correspond to clusters where the co-occurrence probability of each data item within a cluster is at least $1 - \alpha$. We demonstrate how solving the core clustering problem is linked to finding the largest maximal cliques in a graph. We show that the method can be used with both clustering and classification algorithms. The proposed method is tested on both simulated and real datasets. The results show that the obtained clusters indeed meet the guarantees on robustness.

We present the Video Ladder Network (VLN) for efficiently generating future video frames. VLN is a neural encoder-decoder model augmented at all layers by both recurrent and feedforward lateral connections. At each layer, these connections form a lateral recurrent residual block, where the feedforward connection represents a skip connection and the recurrent connection represents the residual. Thanks to the recurrent connections, the decoder can exploit temporal summaries generated from all layers of the encoder. This way, the top layer is relieved from the pressure of modeling lower-level spatial and temporal details. Furthermore, we extend the basic version of VLN to incorporate ResNet-style residual blocks in the encoder and decoder, which help improving the prediction results. VLN is trained in self-supervised regime on the Moving MNIST dataset, achieving competitive results while having very simple structure and providing fast inference.

Disjunctive Answer Set Programming (ASP) is a powerful declarative programming paradigm whose main decision problems are located on the second level of the polynomial hierarchy. Identifying tractable fragments and developing efficient algorithms for such fragments are thus important objectives in order to complement the sophisticated ASP systems available to date. Hard problems can become tractable if some problem parameter is bounded by a fixed constant; such problems are then called fixed-parameter tractable (FPT). While several FPT results for ASP exist, parameters that relate to directed or signed graphs representing the program at hand have been neglected so far. In this paper, we first give some negative observations showing that directed width measures on the dependency graph of a program do not lead to FPT results. We then consider the graph parameter of signed clique-width and present a novel dynamic programming algorithm that is FPT w.r.t. this parameter. Clique-width is more general than the well-known treewidth, and, to the best of our knowledge, ours is the first FPT algorithm for bounded clique-width for reasoning problems beyond SAT.

Apple has stayed true to its promise and published its first academic paper on artificial intelligence. The world's most valuable company has traditionally kept its AI research private but earlier this month Ruslan Salakhutdinov, director of AI research at Apple, made a pledge to start being more open. The new Apple paper -- published December 22 and titled "Learning from simulated and unsupervised images through adversarial training" -- gives an insight into some of the techniques that Apple is using to develop AI. In the study, which was published through the Cornell University Library, Apple researchers explain a technique that can be used to improve how an algorithm learns to "see" what is in an image. The paper's six authors state that using synthetic images (such as those seen in a video game), as opposed to real-world images, can be more efficient when it comes to training AI models known as neural networks, which are designed to think in the same way as the human brain. Because synthetic image data is already labelled and annotated while real-world images aren't.

Earlier this month, Apple announced that it would allow its artificial intelligence researchers to publish research papers -- a major shift in the notoriously secretive company's policy. Now, just a few weeks later, the first of these papers has been made public on the preprint server arXiv. The paper -- titled "Learning from Simulated and Unsupervised Images through Adversarial Training"-- deals with intelligent image recognition technology. Specifically, it describes a technique that would enable a program to recognize and decipher computer-generated images. So far, this has not been possible because, as the researchers from Apple note, "synthetic data is often not realistic enough," and increasing the realism is "computationally expensive."

A year ago, a researcher tested Samsung's S Voice digital assistant by telling it he was depressed. "Maybe it's time for you to take a break and get a change of scenery." Researchers found Apple's Siri and Microsoft's Cortana couldn't understand queries involving abuse or sexual assault, according to a study published in March in JAMA Internal Medicine. Amazon's Echo speaker, which houses the Alexa assistant, is mostly used to play music, check the weather and control smart-home devices. Next week's Consumer Electronics Show will show off digital assistants' abilities to make our lives a little easier by adding more voice-powered smarts into our lights, appliances and door locks.

Machine learning (ML) has received a lot of attention recently, and not without good reason. It has already revolutionized fields from image recognition to healthcare to transportation.

A year ago, a researcher tested Samsung's S Voice digital assistant by telling it he was depressed. "Maybe it's time for you to take a break and get a change of scenery." Researchers found Apple's Siri and Microsoft's Cortana couldn't understand queries involving abuse or sexual assault, according to a study published in March in JAMA Internal Medicine. Authorities in Arkansas have served a subpoena to Amazon to gain access to records from the company's Alexa voice assistant. Next week's Consumer Electronics Show will show off digital assistants' abilities to make our lives a little easier by adding more voice-powered smarts into our lights, appliances and door locks.

If Zoe Dewaghe wants ice cream for breakfast, she gets ice cream for breakfast. There's a different set of rules for her younger brother, Zach: He gets oatmeal instead. That's because five-year-old Zoe Dewaghe has a rare genetic disease called Sanfilippo syndrome. She'll gradually lose the ability to speak, to move, to recognize her surroundings. Most patients don't live into adulthood. "Once we found out what was wrong with her, we were like, 'You can eat whatever the heck you want,'" Zoe's mother, Liz, said ruefully. "Because pretty soon, you won't be able to eat." There's no approved treatment for Sanfilippo syndrome.

Over the past several years, Jack Gallant's neuroscience lab has produced a string of papers that sound absurd. In 2011, the lab showed it was possible to recreate movie clips just from observing the brain activity of people watching movies. Using a computer to regenerate the images of a film just by scanning the brain of a person watching one is, in a sense, mind reading. Similarly, in 2015, Gallant's team of scientists predicted which famous paintings people were picturing in their minds by observing the activity of their brains. This year, the team announced in the journal Nature that they had created an "atlas" of where 10,000-plus individual words reside in the brain -- just by having study participants listen to podcasts. How did they do all this?