Improving the interpretability of brain decoding approaches is of primary interest in many neuroimaging studies. Despite extensive studies of this type, at present, there is no formal definition for interpretability of brain decoding models. As a consequence, there is no quantitative measure for evaluating the interpretability of different brain decoding methods. In this paper, we present a simple definition for interpretability of linear brain decoding models. Then, we propose to combine the interpretability and the performance of the brain decoding into a new multi-objective criterion for model selection. Our preliminary results on the toy data show that optimizing the hyper-parameters of the regularized linear classifier based on the proposed criterion results in more informative linear models. The presented definition provides the theoretical background for quantitative evaluation of interpretability in linear brain decoding.

It has been noticed that some external CVIs exhibit a preferential bias towards a larger or smaller number of clusters which is monotonic (directly or inversely) in the number of clusters in candidate partitions. This type of bias is caused by the functional form of the CVI model. For example, the popular Rand index (RI) exhibits a monotone increasing (NCinc) bias, while the Jaccard Index (JI) index suffers from a monotone decreasing (NCdec) bias. This type of bias has been previously recognized in the literature. In this work, we identify a new type of bias arising from the distribution of the ground truth (reference) partition against which candidate partitions are compared. We call this new type of bias ground truth (GT) bias. This type of bias occurs if a change in the reference partition causes a change in the bias status (e.g., NCinc, NCdec) of a CVI. For example, NCinc bias in the RI can be changed to NCdec bias by skewing the distribution of clusters in the ground truth partition. It is important for users to be aware of this new type of biased behaviour, since it may affect the interpretations of CVI results. The objective of this article is to study the empirical and theoretical implications of GT bias. To the best of our knowledge, this is the first extensive study of such a property for external cluster validity indices.

Throughout music history, theorists have identified and documented interpretable rules that capture the decisions of composers. This paper asks, "Can a machine behave like a music theorist?" It presents MUS-ROVER, a self-learning system for automatically discovering rules from symbolic music. MUS-ROVER performs feature learning via $n$-gram models to extract compositional rules --- statistical patterns over the resulting features. We evaluate MUS-ROVER on Bach's (SATB) chorales, demonstrating that it can recover known rules, as well as identify new, characteristic patterns for further study. We discuss how the extracted rules can be used in both machine and human composition.

Current multi-view factorization methods make assumptions that are not acceptable for many kinds of data, and in particular, for graphical data with hierarchical structure. At the same time, current hierarchical methods work only in the single-view setting. We generalize the Treelet Transform to the Multi-View Treelet Transform (MVTT) to allow for the capture of hierarchical structure when multiple views are available. Further, we show how this generalization is consistent with the existing theory and how it might be used in denoising empirical networks and in computing the shared response of functional brain data.

In the standard setting of approachability there are two players and a target set. The players play repeatedly a known vector-valued game where the first player wants to have the average vector-valued payoff converge to the target set which the other player tries to exclude it from this set. We revisit this setting in the spirit of online learning and do not assume that the first player knows the game structure: she receives an arbitrary vector-valued reward vector at every round. She wishes to approach the smallest ("best") possible set given the observed average payoffs in hindsight. This extension of the standard setting has implications even when the original target set is not approachable and when it is not obvious which expansion of it should be approached instead. We show that it is impossible, in general, to approach the best target set in hindsight and propose achievable though ambitious alternative goals. We further propose a concrete strategy to approach these goals. Our method does not require projection onto a target set and amounts to switching between scalar regret minimization algorithms that are performed in episodes. Applications to global cost minimization and to approachability under sample path constraints are considered.

You may be right to be paranoid about government surveillance and tracking, because the FBI may not be playing by even its own rules. A report released Wednesday by the U.S. Government Accountability Office (GAO) revealed that the FBI's facial-recognition systems have access to 411.9 million photos of individuals, far more than the 29.7 million previously disclosed. If you've got a passport, or hold a driver's license from Illinois, Michigan, Texas, North Carolina or a dozen other states, you're probably in there. The GAO report also criticized the FBI for not adequately performing required assessments of the systems' impact on privacy. The 382 million additional images the public was not aware of until yesterday were obtained by the FBI from the Department of State, which provided photos from passports and visa applications; the Department of Defense, which provided photos of persons detained by American military forces; and from driver's-license, arrest and prison records held by 16 states.

Intelligent computers that can make decisions like humans may someday be on Hewlett Packard Enterprise's product roadmap. The company has been showing off a prototype computer designed to emulate the way the brain makes calculations. It's based on a new architecture that could define how future computers work. The brain can be seen as an extremely power-efficient biological computer. Brains take in a lot of data related to sights, sounds and smell, which they have to process in parallel without lagging, in terms of computation speed.

When I was working on my next pattern classification application, I realized that it might be worthwhile to take a step back and look at the big picture of pattern classification in order to put my previous topics into context and to provide and introduction for the future topics that are going to follow. Pattern classification and machine learning are very hot topics and used in almost every modern application: Optical Character Recognition (OCR) in the post office, spam filtering in our email clients, barcode scanners in the supermarket … the list is endless. In this article, I want to give a quick overview about the main concepts of a typical supervised learning task as a primer for future articles and implementations of various learning algorithms and applications. Predictive modeling is the general concept of building a model that is capable of making predictions. Typically, such a model includes a machine learning algorithm that learns certain properties from a training dataset in order to make those predictions.

Google announced in a blog post on Thursday that it has set up a new AI research group in Europe to focus on machine learning (ML). Machine learning is a field of computer science that gives computers the ability to learn without being explicitly programmed. Google Research, Europe -- as the group is known -- is based out of Google's office in Zurich, Switzerland, which is home to Google's largest engineering office outside the US. Google said the group, which is expected to grow to over 100 people in the coming years, will focus on three key areas: machine intelligence, natural language processing and understanding, and machine perception. Companies like Amazon, Facebook, and Microsoft are all investing heavily in these areas as they look to make their platforms and services more intelligent.

"In 2016, selecting the top achievers was extremely difficult," said Alex Vieux, publisher and CEO of Red Herring. "The variety, depth, disruption and traction we saw from the early stage companies to those with significant scale made it one of the toughest vintages to judge. The North America winners are representative of the amazing ecosystem that never ceases to astound, with new and experienced entrepreneurs continuing to push the barriers of innovation. As one of the winners, Armorway should be proud of its accomplishment under such strong competition." Red Herring's editorial staff evaluated companies on both quantitative and qualitative criteria, such as financial performance, technological innovation and intellectual property, DNA of the founders, business model, customer footprint and market penetration.