Aida is the perfect employee: always courteous, always learning and, as she says, "always at work, 24/7, 365 days a year." Aida, of course, is not a person but a virtual customer-service representative that SEB AB, one of Sweden's biggest banks, is rolling out. The goal is to give the actual humans more time to engage in more complex tasks. After blazing a trail in online and digital banking, Sweden's financial industry is now emerging as a pioneer in the use of artificial intelligence. Besides Aida at SEB, there's Nova, which is a chatbot Nordea Bank AB is introducing at its life and pensions unit in Norway. Swedbank AB is adding to the skills of its virtual assistant, Nina.

BRITAIN'S brightest minds have asked the government to step in and protect vulnerable Britons from the rise of artificially intelligent machines. The Royal Society say that super smart computers which can "learn" and make better decisions than humans will be released within five years time. These machines will help teach our children, nurse the sick and improve social services. They're likely to be driving our cars, pulling our pints and even cooking our dinners, too. But there's a danger that they will create huge inequality across our nation, threatening the very fabric of society.

Driverless vehicles may seem unfamiliar now, but over the coming years you'll start to encounter - or even use them - on a daily basis. Will it mean the end of the driving licence and changes to the rules of the road? It's not uncommon to see a squat white droid trundling along the streets of Greenwich, south-east London, as it delivers takeaway food to the borough's residents at 4mph. In Paris and Helsinki, robot buses are shuttling passengers along city streets, while in Colorado an 18-wheeler truck drove beer 120 miles down a highway - without a driver. Around the world, projects like these are under way to help develop the technology that will ultimately bring driverless cars and other vehicles to our roads. But alongside the issue of whether they will work is another big question: how will pedestrians, cyclists and human drivers be kept safe?

In this work, we design and evaluate a computational learning model that enables a human-robot team to co-develop joint strategies for performing novel tasks that require coordination. The joint strategies are learned through "perturbation training," a human team-training strategy that requires team members to practice variations of a given task to help their team generalize to new variants of that task. We formally define the problem of human-robot perturbation training and develop and evaluate the first end-to-end framework for such training, which incorporates a multi-agent transfer learning algorithm, human-robot co-learning framework and communication protocol. Our transfer learning algorithm, Adaptive Perturbation Training (AdaPT), is a hybrid of transfer and reinforcement learning techniques that learns quickly and robustly for new task variants. We empirically validate the benefits of AdaPT through comparison to other hybrid reinforcement and transfer learning techniques aimed at transferring knowledge from multiple source tasks to a single target task. We also demonstrate that AdaPT's rapid learning supports live interaction between a person and a robot, during which the human-robot team trains to achieve a high level of performance for new task variants. We augment AdaPT with a co-learning framework and a computational bi-directional communication protocol so that the robot can co-train with a person during live interaction. Results from large-scale human subject experiments (n=48) indicate that AdaPT enables an agent to learn in a manner compatible with a human's own learning process, and that a robot undergoing perturbation training with a human results in a high level of team performance. Finally, we demonstrate that human-robot training using AdaPT in a simulation environment produces effective performance for a team incorporating an embodied robot partner.

In this paper we show that reporting a single performance score is insufficient to compare non-deterministic approaches. We demonstrate for common sequence tagging tasks that the seed value for the random number generator can result in statistically significant (p < 10^-4) differences for state-of-the-art systems. For two recent systems for NER, we observe an absolute difference of one percentage point F1-score depending on the selected seed value, making these systems perceived either as state-of-the-art or mediocre. Instead of publishing and reporting single performance scores, we propose to compare score distributions based on multiple executions. Based on the evaluation of 50.000 LSTM-networks for five sequence tagging tasks, we present network architectures that produce both superior performance as well as are more stable with respect to the remaining hyperparameters.

Multipath is among the major sources of errors in precise positioning using GPS and continues to be extensively studied. Two Fast Fourier Transform (FFT)-based detectors are presented in this paper as GPS multipath detection techniques. The detectors are formulated as binary hypothesis tests under the assumption that the multipath exists for a sufficient time frame that allows its detection based on the quadrature arm of the coherent Early-minus-Late discriminator (Q EmL) for a scalar tracking loop (STL) or on the quadrature (Q EmL) and/or in-phase arm (I EmL) for a vector tracking loop (VTL), using an observation window of N samples. Performance analysis of the suggested detectors is done on multipath signal data acquired from the multipath environment simulator developed by the German Aerospace Centre (DLR) as well as on multipath data from real GPS signals. Application of the detection tests to correlator outputs of scalar and vector tracking loops shows that they may be used to exclude multipath contaminated satellites from the navigation solution. These detection techniques can be extended to other Global Navigation Satellite Systems (GNSS) such as GLONASS, Galileo and Beidou.

Trace norm regularization is a widely used approach for learning low rank matrices. A standard optimization strategy is based on formulating the problem as one of low rank matrix factorization which, however, leads to a non-convex problem. In practice this approach works well, and it is often computationally faster than standard convex solvers such as proximal gradient methods. Nevertheless, it is not guaranteed to converge to a global optimum, and the optimization can be trapped at poor stationary points. In this paper we show that it is possible to characterize all critical points of the non-convex problem. This allows us to provide an efficient criterion to determine whether a critical point is also a global minimizer. Our analysis suggests an iterative meta-algorithm that dynamically expands the parameter space and allows the optimization to escape any non-global critical point, thereby converging to a global minimizer. The algorithm can be applied to problems such as matrix completion or multitask learning, and our analysis holds for any random initialization of the factor matrices. Finally, we confirm the good performance of the algorithm on synthetic and real datasets.

The MAP-Elites algorithm produces a set of high-performing solutions that vary according to features defined by the user. This technique has the potential to be a powerful tool for design space exploration, but is limited by the need for numerous evaluations. The Surrogate-Assisted Illumination algorithm (SAIL), introduced here, integrates approximative models and intelligent sampling of the objective function to minimize the number of evaluations required by MAP-Elites. The ability of SAIL to efficiently produce both accurate models and diverse high performing solutions is illustrated on a 2D airfoil design problem. The search space is divided into bins, each holding a design with a different combination of features. In each bin SAIL produces a better performing solution than MAP-Elites, and requires several orders of magnitude fewer evaluations. The CMA-ES algorithm was used to produce an optimal design in each bin: with the same number of evaluations required by CMA-ES to find a near-optimal solution in a single bin, SAIL finds solutions of similar quality in every bin.

Recurrent neural networks show state-of-the-art results in many text analysis tasks but often require a lot of memory to store their weights. Recently proposed Sparse V ariational Dropout (Molchanov et al., 2017) eliminates the majority of the weights in a feed-forward neural network without significant loss of quality. We apply this technique to sparsify recurrent neural networks. To account for recurrent specifics we also rely on Binary V ariational Dropout for RNN (Gal & Ghahramani, 2016b). We report 99.5% sparsity level on sentiment analysis task without a quality drop and up to 87% sparsity level on language modeling task with slight loss of accuracy.

We study learning problems in the general setup, for arbitrary classes of functions $F$, distributions $X$ and targets $Y$. Because proper learning procedures, i.e., procedures that are only allowed to select functions in $F$, tend to perform poorly unless the problem satisfies some additional structural property (e.g., that $F$ is convex), we consider unrestricted learning procedures, that is, procedures that are free to choose functions outside the given class $F$. We present a new unrestricted procedure that is optimal in a very strong sense: it attains the best possible accuracy/confidence tradeoff for (almost) any triplet $(F,X,Y)$, including in heavy-tailed problems. Moreover, the tradeoff the procedure attains coincides with what one would expect if $F$ were convex, even when $F$ is not; and when $F$ happens to be convex, the procedure is proper; thus, the unrestricted procedure is actually optimal in both realms, for convex classes as a proper procedure and for arbitrary classes as an unrestricted procedure. The notion of optimality we consider is problem specific: our procedure performs with the best accuracy/confidence tradeoff one can hope to achieve for each individual problem. As such, it is a significantly stronger property than the standard `worst-case' notion, in which one considers optimality as the best uniform estimate that holds for a relatively large family of problems. Thanks to the sharp and problem-specific estimates we obtain, classical, worst-case bounds are immediate outcomes of our main result.