A big challenge in algorithmic composition is to devise a model that is both easily trainable and able to reproduce the long-range temporal dependencies typical of music. Here we investigate how artificial neural networks can be trained on a large corpus of melodies and turned into automated music composers able to generate new melodies coherent with the style they have been trained on. We employ gated recurrent unit networks that have been shown to be particularly efficient in learning complex sequential activations with arbitrary long time lags. Our model processes rhythm and melody in parallel while modeling the relation between these two features. Using such an approach, we were able to generate interesting complete melodies or suggest possible continuations of a melody fragment that is coherent with the characteristics of the fragment itself.

We introduce a variational Bayesian neural network where the parameters are governed via a probability distribution on random matrices. Specifically, we employ a matrix variate Gaussian \cite{gupta1999matrix} parameter posterior distribution where we explicitly model the covariance among the input and output dimensions of each layer. Furthermore, with approximate covariance matrices we can achieve a more efficient way to represent those correlations that is also cheaper than fully factorized parameter posteriors. We further show that with the "local reprarametrization trick" \cite{kingma2015variational} on this posterior distribution we arrive at a Gaussian Process \cite{rasmussen2006gaussian} interpretation of the hidden units in each layer and we, similarly with \cite{gal2015dropout}, provide connections with deep Gaussian processes. We continue in taking advantage of this duality and incorporate "pseudo-data" \cite{snelson2005sparse} in our model, which in turn allows for more efficient sampling while maintaining the properties of the original model. The validity of the proposed approach is verified through extensive experiments.

We characterize the combinatorial structure of conditionally-i.i.d. sequences of negative binomial processes with a common beta process base measure. In Bayesian nonparametric applications, such processes have served as models for latent multisets of features underlying data. Analogously, random subsets arise from conditionally-i.i.d. sequences of Bernoulli processes with a common beta process base measure, in which case the combinatorial structure is described by the Indian buffet process. Our results give a count analogue of the Indian buffet process, which we call a negative binomial Indian buffet process. As an intermediate step toward this goal, we provide a construction for the beta negative binomial process that avoids a representation of the underlying beta process base measure. We describe the key Markov kernels needed to use a NB-IBP representation in a Markov Chain Monte Carlo algorithm targeting a posterior distribution.

In this paper, we tackle the question of discovering an effective set of spatial filters to solve hyperspectral classification problems. Instead of fixing a priori the filters and their parameters using expert knowledge, we let the model find them within random draws in the (possibly infinite) space of possible filters. We define an active set feature learner that includes in the model only features that improve the classifier. To this end, we consider a fast and linear classifier, multiclass logistic classification, and show that with a good representation (the filters discovered), such a simple classifier can reach at least state of the art performances. We apply the proposed active set learner in four hyperspectral image classification problems, including agricultural and urban classification at different resolutions, as well as multimodal data. We also propose a hierarchical setting, which allows to generate more complex banks of features that can better describe the nonlinearities present in the data.

In this paper, we study the effect of different regularizers and their implications in high dimensional image classification and sparse linear unmixing. Although kernelization or sparse methods are globally accepted solutions for processing data in high dimensions, we present here a study on the impact of the form of regularization used and its parametrization. We consider regularization via traditional squared (2) and sparsity-promoting (1) norms, as well as more unconventional nonconvex regularizers (p and Log Sum Penalty). We compare their properties and advantages on several classification and linear unmixing tasks and provide advices on the choice of the best regularizer for the problem at hand. Finally, we also provide a fully functional toolbox for the community.

Boston Limited have introduced the latest weapon to their machine learning armoury in the guise of the Boston ANNA Pascal, a new NVIDIA Tesla GPU-based solution at ISC 2016 in Frankfurt, Germany. The revolutionary NVIDIA Pascal architecture is purpose-built to act as the engine of computers that learn, see, and simulate our world. Leveraging this technology, the Boston ANNA Pascal should be considered for the title of the'world's fastest deep learning appliance'. By introducing four ground-breaking technologies, the appliance enables the system to deliver lightning fast, absolute performance to HPC and deep learning workloads with infinite computing needs. The Boston ANNA Pascal redefines what is possible for the research community and the industry; helping solve many big data problems such as computer vision, speech recognition, and natural language processing.

On 14 June, news broke that someone had hacked into computers at the US Democratic National Committee, exposing opposition research on Republican presidential candidate Donald Trump, as well as a trove of chat logs and emails. Some blamed Russia – although as ever details are unclear. The same day, NATO announced that it was designating cyberspace as an "operational domain" for war alongside land, sea and air. Reports of one country attacking the computer systems of another – like this week's hack on the Democrats, last year's Chinese breach of the US Office of Personnel Management, or North Korea's attack on Sony in 2014 – have become common. The details of hacks may differ, but the story is a familiar one. Does NATO's announcement change anything?

Altoros brings "software assembly lines" into organizations through training, deployment, and integration of solutions offered by the Cloud Foundry ecosystem. As a result, customers of Altoros discover and monetize application-driven competitive advantages sooner than competition by using Cloud Foundry-based "software factories" and "data lakes." With 250 employees across 8 countries, Altoros is behind some of the world's largest Cloud Foundry deployments.

The traditional definition of artificial intelligence is the ability of machines to execute tasks and solve problems in ways normally attributed to humans. Some tasks that we consider simple--recognizing an object in a photo, driving a car--are incredibly complex for AI. Machines can surpass us when it comes to things like playing chess, but those machines are limited by the manual nature of their programming; a 30 gadget can beat us at a board game, but it can't do--or learn to do--anything else. This is where machine learning comes in. Show millions of cat photos to a machine, and it will hone its algorithms to improve at recognizing pictures of cats.

In 1948 a young man by the name of Alan Turing penned a report entitled "Intelligent Machinery." The opening sentence "I propose to investigate the question as to whether it is possible for machinery to show intelligent behavior" (1) had instantly set the stage for what we today would call AI, or Artificial Intelligence. And ever since that time the world has looked towards the future with glossy stares and dreams of such a day. Turing, in 1935, was the pioneering mind behind the modern computer, though most people recognize the name based on the human computer test called the Turing Test. The test was introduced by Alan in a 1950 paper titled "Computing Machinery and Intelligence," and his goal was to "test if a machine's ability could exhibit intelligent behavior equivalent to, or indistinguishable from, that of a human."