In this paper we study several classes of stochastic optimization algorithms enriched with heavy ball momentum. Among the methods studied are: stochastic gradient descent, stochastic Newton, stochastic proximal point and stochastic dual subspace ascent. This is the first time momentum variants of several of these methods are studied. We choose to perform our analysis in a setting in which all of the above methods are equivalent. We prove global nonassymptotic linear convergence rates for all methods and various measures of success, including primal function values, primal iterates (in L2 sense), and dual function values. We also show that the primal iterates converge at an accelerated linear rate in the L1 sense. This is the first time a linear rate is shown for the stochastic heavy ball method (i.e., stochastic gradient descent method with momentum). Under somewhat weaker conditions, we establish a sublinear convergence rate for Cesaro averages of primal iterates. Moreover, we propose a novel concept, which we call stochastic momentum, aimed at decreasing the cost of performing the momentum step. We prove linear convergence of several stochastic methods with stochastic momentum, and show that in some sparse data regimes and for sufficiently small momentum parameters, these methods enjoy better overall complexity than methods with deterministic momentum. Finally, we perform extensive numerical testing on artificial and real datasets, including data coming from average consensus problems.

In high dimensional regression settings, sparsity enforcing penalties have proved useful to regularize the data-fitting term. A recently introduced technique called screening rules propose to ignore some variables in the optimization leveraging the expected sparsity of the solutions and consequently leading to faster solvers. When the procedure is guaranteed not to discard variables wrongly the rules are said to be safe. In this work, we propose a unifying framework for generalized linear models regularized with standard sparsity enforcing penalties such as $\ell_1$ or $\ell_1/\ell_2$ norms. Our technique allows to discard safely more variables than previously considered safe rules, particularly for low regularization parameters. Our proposed Gap Safe rules (so called because they rely on duality gap computation) can cope with any iterative solver but are particularly well suited to (block) coordinate descent methods. Applied to many standard learning tasks, Lasso, Sparse-Group Lasso, multi-task Lasso, binary and multinomial logistic regression, etc., we report significant speed-ups compared to previously proposed safe rules on all tested data sets.

In the light of the UK's new industrial strategy and budget, as well as the ODI's recent participation in a House of Lords evidence session around how AI and personal data should be owned, managed, valued and used for the benefit of society, the ODI's Head of Technology Olivier Thereaux examines our work in this area. Artificial intelligence (AI) is currently enjoying a renaissance in industry and popular imagination, and in the most recent UK government budget. AI's popularity can be partly explained by the fact that, for the first time, we have enough large-scale data for training AI systems. There are public datasets for computer vision, natural language, speech and many more non-public datasets within businesses and governments. Recent improvements in hardware are also making it more cost-effective to train and run machine-learning models.

Driving in winter conditions can be slow and hazardous, even for skilled drivers. The self-driving cars in development today are generally designed and tested on city streets, with curbs and lane markings and GPS maps to rely on. But what happens when you live in a country like Finland, where roads covered with several inches of snow are a fact of life every year? Researchers at the VTT Technical Research Centre are tackling that problem head-on with Martti, an autonomous vehicle specifically programmed to safely navigate public roads blanketed in snow. Built on a Volkswagen Touareg, it's equipped with a variety of antennas, sensors, cameras, and laser scanners.

Artificial Intelligence (AI), does not yet encompass armies of killer-robots roaming the planet. However it has made some inroads into our day-to-day lives from the mundane (voice recognition software in telephone call centres) to the more interesting (driverless cars are no doubt on the way). Within higher education some areas of AI are well-established such as automatic plagiarism-detection systems for student submissions like'Turnitin'. However, to date we have barely scratched the surface of what AI is capable of. Now, industry and technology experts are predicting that AI will expand to take over many routine tasks in the coming years and decades.

Nowadays web-sites needs to handle huge amount of traffic. We can leverage that fact and capture user interactions with the application. Next, we can analyze users behavior and capture patterns on which we are able to react properly. In applications that needs to deal with huge amount of traffic it is very hard to detect anomalies. We'll learn how to apply clustering to find anomalies in web traffic.

These days artificial intelligence is so advanced that robots trade shares, make restaurants suggestions and diagnose diseases. But can a robot get a dance floor jumping? It is a question that Prague's Karlovy Lazne Music Club has endeavoured to answer by employing a specially adapted former automotive industry robot as a DJ in the popular nightspot. These days artificial intelligence is so advanced that robots trade shares, make restaurants suggestions and diagnose diseases. But can a robot get a dance floor jumping?

Eighty-five per cent of senior executives plan to invest in artificial intelligence (AI) and the Internet of Things (IoT) by 2020, according to a new survey of UK digital leaders by Deloitte. The findings come from the first edition of a new regular report from Deloitte, the Digital Disruption Index. The index will track investment in digital technologies and create a detailed picture of their impact on the largest and most influential business and public sector bodies. The first edition includes responses from 51 organisations with a combined market value of £229bn. Over half of survey respondents expect that by 2020, they will invest more than £10 million in digital technologies and ways of working – such as AI, cloud, robotics, blockchain, analytics, the IoT, and virtual and augmented reality.

LONDON: Scientists are combining Twitter, citizen science and cutting-edge artificial intelligence (AI) techniques to develop an early-warning system for flood-prone communities. Researchers from the University of Dundee in the UK have shown how AI can be used to extract data from Twitter and crowdsourced information from mobile phone apps to build up hyper-resolution monitoring of urban flooding. Urban flooding is difficult to monitor due to complexities in data collection and processing. This prevents detailed risk analysis, flooding control, and the validation of numerical models. Researchers set about trying to solve this problem by exploring how the latest AI technology can be used to mine social media and apps for the data that users provide.

It's hard to believe how fast 2017 has already gone by here at BigML. It has been a banner year with many firsts thanks to the Machine Learning freight train running on all cylinders across the global economy. Gone are the days, when we often found ourselves describing what Machine Learning is and why it matters for businesses. Instead, here we are in the closing days of 2017 exchanging ideas on new use cases Machine Learning can be applied towards with business leaders. When things happen so fast, one can sometimes find it a challenge to stop and reflect on milestones and achievements.