We apply the label of "genius" to everyone today, from our greatest achievers to exceptional children, and we even nickname our favorite musicians after it. But what, exactly, is genius? Is it someone who is crazy enough to tackle problems we are even afraid to acknowledge, or is it just someone who is better than us at living our dreams. We are the ones who marvel and wonder, longing for the salvation genius might bring. We are the ones who pay homage and obeisance.

liquidSVM is a package written in C++ that provides SVM-type solvers for various classification and regression tasks. Because of a fully integrated hyper-parameter selection, very carefully implemented solvers, multi-threading and GPU support, and several built-in data decomposition strategies it provides unprecedented speed for small training sizes as well as for data sets of tens of millions of samples. Besides the C++ API and a command line interface, bindings to R, MATLAB, Java, Python, and Spark are available. We present a brief description of the package and report experimental comparisons to other SVM packages.

Nested Chinese Restaurant Process (nCRP) topic models are powerful nonparametric Bayesian methods to extract a topic hierarchy from a given text corpus, where the hierarchical structure is automatically determined by the data. Hierarchical Latent Dirichlet Allocation (hLDA) is a popular instance of nCRP topic models. However, hLDA has only been evaluated at small scale, because the existing collapsed Gibbs sampling and instantiated weight variational inference algorithms either are not scalable or sacrifice inference quality with mean-field assumptions. Moreover, an efficient distributed implementation of the data structures, such as dynamically growing count matrices and trees, is challenging. In this paper, we propose a novel partially collapsed Gibbs sampling (PCGS) algorithm, which combines the advantages of collapsed and instantiated weight algorithms to achieve good scalability as well as high model quality. An initialization strategy is presented to further improve the model quality. Finally, we propose an efficient distributed implementation of PCGS through vectorization, pre-processing, and a careful design of the concurrent data structures and communication strategy. Empirical studies show that our algorithm is 111 times more efficient than the previous open-source implementation for hLDA, with comparable or even better model quality. Our distributed implementation can extract 1,722 topics from a 131-million-document corpus with 28 billion tokens, which is 4-5 orders of magnitude larger than the previous largest corpus, with 50 machines in 7 hours.

Partial Least Squares (PLS) methods have been heavily exploited to analyse the association between two blocs of data. These powerful approaches can be applied to data sets where the number of variables is greater than the number of observations and in presence of high collinearity between variables. Different sparse versions of PLS have been developed to integrate multiple data sets while simultaneously selecting the contributing variables. Sparse modelling is a key factor in obtaining better estimators and identifying associations between multiple data sets. The cornerstone of the sparsity version of PLS methods is the link between the SVD of a matrix (constructed from deflated versions of the original matrices of data) and least squares minimisation in linear regression. We present here an accurate description of the most popular PLS methods, alongside their mathematical proofs. A unified algorithm is proposed to perform all four types of PLS including their regularised versions. Various approaches to decrease the computation time are offered, and we show how the whole procedure can be scalable to big data sets.

Stochastic Neighbor Embedding and its variants are widely used dimensionality reduction techniques -- despite their popularity, no theoretical results are known. We prove that the optimal SNE embedding of well-separated clusters from high dimensions to any Euclidean space R^d manages to successfully separate the clusters in a quantitative way. The result also applies to a larger family of methods including a variant of t-SNE.

Think that artificial intelligence isn't intelligent yet? Quick: What do you think of when you hear the words "artificial intelligence?" You might think of Siri or Alexa. Maybe you picture robots that are coming to steal your job. Or perhaps you think of technology that turns against its inventors and spells the end of the human race. Whatever your personal stance may be, according to recent headlines, the population is split when it comes to their belief in AI.

The machines haven't taken over. However, they are seeping their way into our lives, affecting how we live, work and entertain ourselves. From voice-powered personal assistants like Siri and Alexa, to more underlying and fundamental technologies such as behavioral algorithms, suggestive searches and autonomously-powered self-driving vehicles boasting powerful predictive capabilities, there are several examples and applications of artificial intellgience in use today. However, the technology is still in its infancy. What many companies are calling A.I. today, aren't necessarily so.

Usually, biologically inspired robotics is about figuring out evolution's clever tricks and then trying to apply them to your robot to make it faster or more efficient or more skilled or whatever. It isn't very often that a robot ends up beating nature at its own game--evolution is a very intelligent designer, and roboticists are going up against a half billion years of trial and error. In an article published last week in Nature Communications, researchers from EPFL, in Lausanne, Switzerland, managed to show that for legged hexapods, a bipedal gait (using just two active legs at once) is often the fastest and most efficient way of moving, even though insects use a tripedal gait instead. Generally, the most efficient way of moving (especially moving quickly) for legged animals is to minimize the amount of time that you've got legs making contact with the ground. You see this all the time in mammals, the fastest of which prioritize flight phases, where motion is more like a sequence of dynamic jumps as opposed to just a sped-up walk.

Businessman and Dallas Mavericks owner Mark Cuban turned to Twitter to warn about robots' threat to unemployment. "Automation is going to cause unemployment and we need to prepare for it," Cuban said Sunday. The tweet also included a link to warnings about artificial intelligence from tech leaders, including Tesla CEO Elon Musk, Bill Gates and Stephen Hawking. Cuban didn't elaborate on the subject, but in a recent interview with CNBC he said President Donald Trump and his administration don't understand technology advancements in machine learning and artificial intelligence. Cuban is a strong critic of Trump and had endorsed his opponent, former Secretary of State Hillary Clinton, during the presidential campaign.

During the three years I've spent researching and writing about shyness, one of the most common questions people ask is about the relationship between shyness and technology. Are the internet and the cellphone causing our social skills to atrophy? I often hear this from parents of shy teenagers, who are worried that their children are spending more time with their devices than with their peers. The shy aren't necessarily antisocial; they are just differently social. They learn to regulate their sociability and communicate in indirect or tangential ways.