The analysis of manifold-valued data requires efficient tools from Riemannian geometry to cope with the computational complexity at stake. This complexity arises from the always-increasing dimension of the data, and the absence of closed-form expressions to basic operations such as the Riemannian logarithm. In this paper, we adapt a generic numerical scheme recently introduced for computing parallel transport along geodesics in a Riemannian manifold to finite-dimensional manifolds of diffeomorphisms. We provide a qualitative and quantitative analysis of its behavior on high-dimensional manifolds, and investigate an application with the prediction of brain structures progression.

We propose a method to predict the subject-specific longitudinal progression of brain structures extracted from baseline MRI, and evaluate its performance on Alzheimer's disease data. The disease progression is modeled as a trajectory on a group of diffeomorphisms in the context of large deformation diffeomorphic metric mapping (LDDMM). We first exhibit the limited predictive abilities of geodesic regression extrapolation on this group. Building on the recent concept of parallel curves in shape manifolds, we then introduce a second predictive protocol which personalizes previously learned trajectories to new subjects, and investigate the relative performances of two parallel shifting paradigms. This design only requires the baseline imaging data. Finally, coefficients encoding the disease dynamics are obtained from longitudinal cognitive measurements for each subject, and exploited to refine our methodology which is demonstrated to successfully predict the follow-up visits.

Big spatio-temporal datasets, available through both open and administrative data sources, offer significant potential for social science research. The magnitude of the data allows for increased resolution and analysis at individual level. While there are recent advances in forecasting techniques for highly granular temporal data, little attention is given to segmenting the time series and finding homogeneous patterns. In this paper, it is proposed to estimate behavioral profiles of individuals' activities over time using Gaussian Process-based models. In particular, the aim is to investigate how individuals or groups may be clustered according to the model parameters. Such a Bayesian non-parametric method is then tested by looking at the predictability of the segments using a combination of models to fit different parts of the temporal profiles. Model validity is then tested on a set of holdout data. The dataset consists of half hourly energy consumption records from smart meters from more than 100,000 households in the UK and covers the period from 2015 to 2016. The methodological approach developed in the paper may be easily applied to datasets of similar structure and granularity, for example social media data, and may lead to improved accuracy in the prediction of social dynamics and behavior.

We address the two fundamental problems of spatial field reconstruction and sensor selection in heterogeneous sensor networks: (i) how to efficiently perform spatial field reconstruction based on measurements obtained simultaneously from networks with both high and low quality sensors; and (ii) how to perform query based sensor set selection with predictive MSE performance guarantee. For the first problem, we developed a low complexity algorithm based on the spatial best linear unbiased estimator (S-BLUE). Next, building on the S-BLUE, we address the second problem, and develop an efficient algorithm for query based sensor set selection with performance guarantee. Our algorithm is based on the Cross Entropy method which solves the combinatorial optimization problem in an efficient manner.

Neural networks are generally built by interleaving (adaptable) linear layers with (fixed) nonlinear activation functions. To increase their flexibility, several authors have proposed methods for adapting the activation functions themselves, endowing them with varying degrees of flexibility. None of these approaches, however, have gained wide acceptance in practice, and research in this topic remains open. In this paper, we introduce a novel family of flexible activation functions that are based on an inexpensive kernel expansion at every neuron. Leveraging over several properties of kernel-based models, we propose multiple variations for designing and initializing these kernel activation functions (KAFs), including a multidimensional scheme allowing to nonlinearly combine information from different paths in the network. The resulting KAFs can approximate any mapping defined over a subset of the real line, either convex or nonconvex. Furthermore, they are smooth over their entire domain, linear in their parameters, and they can be regularized using any known scheme, including the use of $\ell_1$ penalties to enforce sparseness. To the best of our knowledge, no other known model satisfies all these properties simultaneously. In addition, we provide a relatively complete overview on alternative techniques for adapting the activation functions, which is currently lacking in the literature. A large set of experiments validates our proposal.

Conscious robots with the capabilities of human beings are one of the oldest sci-fi tropes; a threatening blend of human and machine that could turn from friend to foe at a moment's notice. With recent developments in artificial intelligence (AI) systems, there are many who both hope and worry that we will advance this technology far enough to actually create a machine with consciousness. And neuroscience researchers truly believe that they might be on the path to one day achieving this. In a paper published on Friday in Science, Stanislas Dehaene from Collège de France in Paris led a team of neuroscientists to get a better grasp on the computational aspect of consciousness and, as a followup, if the quantitative phenomena under study could ever be reproduced in a machine. The team framed consciousness not as a singular concept, but as three distinct types. As for the potential to integrate human computational power into robotics, they concluded that only one of these three types has been achieved by computers -- so even if it is possible, there is still oceans of work to be done.

One thing the government is promising in the budget is a change to the law to allow more driverless cars to be tested on Britain's roads.

Electric and driverless cars in the UK have been given a major boost by the Chancellor today. A total of £540 million ($716 million) is being invested in electric cars, including £400 million ($530 million) on building more electric car charging points. While there are currently only 4,500 charging stations in the UK, the investment will enable this number to dramatically increase. Philip Hammond said this will pave the way for driverless vehicles, and added that red tape will be cut to allow technology firms to test autonomous cars on public roads by 2021. The budget revealed that £400 million ($530 million) is being invested in electric car charging infrastructure, £100 million ($132 million) is being invested in plug-in car grants and £40 million ($53 million) is being invested in electric car charging research and development.

In a bid to lower emissions in the capital and reduce the footprint of its vehicles on the road, global delivery firm UPS has begun trialling a new electric-powered bike trailer on the streets of London. The concept, built as part of the Low Impact City Logistics project, attaches to the back of a pedal cycle and utilises a "net-neutral" technology. This then allows couriers to transport up to 200 kilograms without requiring any additional effort on their part. The project was formalised following a pitch process back in 2016. Innovate UK, the quango behind numerous self-driving car projects across Britain, stumped up £10 million for a new collaborative research and development project and five organizations answered the call.

The Government is to spend hundreds of millions of pounds encouraging people to make electric cars that drive themselves. It will spend huge amounts of money to try and incentivise electric vehicles. Then eventually those cars will start driving themselves around the country – with Chancellor Philip Hammond backing a plan to have them making their own way by 2021. Jeremy Corbyn used the news about driverless vehicles to joke about having tested "backseat driving" in the Government, which has been bitterly divided before the Budget. Mr Hammond said the technology was being introduced because the Government saw it as the future.