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.

While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- \textit{Internal Covariate Shift}-- the current solution has certain drawbacks. For instance, BN depends on batch statistics for layerwise input normalization during training which makes the estimates of mean and standard deviation of input (distribution) to hidden layers inaccurate due to shifting parameter values (especially during initial training epochs). Another fundamental problem with BN is that it cannot be used with batch-size $ 1 $ during training. We address these drawbacks of BN by proposing a non-adaptive normalization technique for removing covariate shift, that we call \textit{Normalization Propagation}. Our approach does not depend on batch statistics, but rather uses a data-independent parametric estimate of mean and standard-deviation in every layer thus being computationally faster compared with BN. We exploit the observation that the pre-activation before Rectified Linear Units follow Gaussian distribution in deep networks, and that once the first and second order statistics of any given dataset are normalized, we can forward propagate this normalization without the need for recalculating the approximate statistics for hidden layers.

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.

"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.

Over the last year, stories pointing to a bright future for deep neural networks and deep learning in general have proliferated. However, most of what we have seen has been centered on the use of deep learning to power consumer services. Speech and image recognition, video analysis, and other features have spun from deep learning developments, but from the mainstream view, it would seem that scientific computing use cases are still limited. Deep neural networks present an entirely different way of thinking about a problem set and the data that feeds it. While there are established approaches for images and speech patterns both in terms of training and inference, research areas that could benefit are still lagging somewhat behind.

"Knowledge workers spend a significant amount of time searching for information, either through standard search engines or through specialized tools", said Pablo Brenner, co-founder of Collokia. "In many situations, co-workers have already searched for similar information, but the work is recreated because there is no knowledge or experience sharing, leaving them unaware. Collokia s platform automatically identifies such collaboration opportunities and eliminates the time wasted on redundant research efforts. For example, when searching for a specific subject, Collokia alerts users to similar activities that have already been completed, offering recommendations and connecting them with others within the organization that have expertise on the information they are seeking." In contrast with most collaboration platforms where sharing information requires extra effort by the employee, Collokia s knowledge mapping, collection and distribution is completely transparent and effortless for all involved parties.

Researchers recently used an artificial intelligence to run a complex experiment, which it learnt to perform from scratch in under an hour. "A simple computer program would have taken longer than the age of the Universe to run through all the combinations and work this out," said co-lead researcher Paul Wigley from the Australian National University Research School of Physics and Engineering. This suggests that even physicists are on track to having their jobs augmented if not outright captured by artificial intelligence. The experiment involved the creation of a Bose-Einstein condensate, an extremely cold gas trapped in a laser beam. At a billionth of a degree Kelvin, it is even colder than outer space.