Researchers from the University of Warsaw, Google AI and deepsense.ai The goal of the experiment is to end-to-end train an artificial intelligence to play video games fully inside a computation graph. A team from the University of Warsaw, made up of Piotr Miłoś, Błażej Osiński and Henryk Michalewski, has started a collaboration on reinforcement learning research with Łukasz Kaiser from the Google Brain team and with researchers from deepsense.ai. This project is connected to a research program on RL that deepsense.ai In the experiment, an artificial intelligence will be end-to-end trained to play video games fully inside a computation graph.

The convergence speed of stochastic gradient descent (SGD) can be improved by actively selecting mini-batches. We explore sampling schemes where similar data points are less likely to be selected in the same mini-batch. In particular, we prove that such repulsive sampling schemes lowers the variance of the gradient estimator. This generalizes recent work on using Determinantal Point Processes (DPPs) for mini-batch diversification (Zhang et al., 2017) to the broader class of repulsive point processes. We first show that the phenomenon of variance reduction by diversified sampling generalizes in particular to non-stationary point processes. We then show that other point processes may be computationally much more efficient than DPPs. In particular, we propose and investigate Poisson Disk sampling---frequently encountered in the computer graphics community---for this task. We show empirically that our approach improves over standard SGD both in terms of convergence speed as well as final model performance.

We consider a problem of multiclass classification, where the training sample $S_n = \{(X_i, Y_i)\}_{i=1}^n$ is generated from the model $\mathbb p(Y = m | X = x) = \theta_m(x)$, $1 \leq m \leq M$, and $\theta_1(x), \dots, \theta_M(x)$ are unknown Lipschitz functions. Given a test point $X$, our goal is to estimate $\theta_1(X), \dots, \theta_M(X)$. An approach based on nonparametric smoothing uses a localization technique, i.e. the weight of observation $(X_i, Y_i)$ depends on the distance between $X_i$ and $X$. However, local estimates strongly depend on localizing scheme. In our solution we fix several schemes $W_1, \dots, W_K$, compute corresponding local estimates $\widetilde\theta^{(1)}, \dots, \widetilde\theta^{(K)}$ for each of them and apply an aggregation procedure. We propose an algorithm, which constructs a convex combination of the estimates $\widetilde\theta^{(1)}, \dots, \widetilde\theta^{(K)}$ such that the aggregated estimate behaves approximately as well as the best one from the collection $\widetilde\theta^{(1)}, \dots, \widetilde\theta^{(K)}$. We also study theoretical properties of the procedure, prove oracle results and establish rates of convergence under mild assumptions.

Neural network based architectures used for sound recognition are usually adapted from other application domains, which may not harness sound related properties. The ConditionaL Neural Network (CLNN) is designed to consider the relational properties across frames in a temporal signal, and its extension the Masked ConditionaL Neural Network (MCLNN) embeds a filterbank behavior within the network, which enforces the network to learn in frequency bands rather than bins. Additionally, it automates the exploration of different feature combinations analogous to handcrafting the optimum combination of features for a recognition task. We applied the MCLNN to the environmental sounds of the ESC-10 dataset. The MCLNN achieved competitive accuracies compared to state-of-the-art convolutional neural networks and hand-crafted attempts.

The appeal of metric evaluation of research impact has attracted considerable interest in recent times. Although the public at large and administrative bodies are much interested in the idea, scientists and other researchers are much more cautious, insisting that metrics are but an auxiliary instrument to the qualitative peer-based judgement. The goal of this article is to propose availing of such a well positioned construct as domain taxonomy as a tool for directly assessing the scope and quality of research. We first show how taxonomies can be used to analyse the scope and perspectives of a set of research projects or papers. Then we proceed to define a research team or researcher's rank by those nodes in the hierarchy that have been created or significantly transformed by the results of the researcher. An experimental test of the approach in the data analysis domain is described. Although the concept of taxonomy seems rather simplistic to describe all the richness of a research domain, its changes and use can be made transparent and subject to open discussions.

Automated process discovery is a class of process mining methods that allow analysts to extract business process models from event logs. Traditional process discovery methods extract process models from a snapshot of an event log stored in its entirety. In some scenarios, however, events keep coming with a high arrival rate to the extent that it is impractical to store the entire event log and to continuously re-discover a process model from scratch. Such scenarios require online process discovery approaches. Given an event stream produced by the execution of a business process, the goal of an online process discovery method is to maintain a continuously updated model of the process with a bounded amount of memory while at the same time achieving similar accuracy as offline methods. However, existing online discovery approaches require relatively large amounts of memory to achieve levels of accuracy comparable to that of offline methods. Therefore, this paper proposes an approach that addresses this limitation by mapping the problem of online process discovery to that of cache memory management, and applying well-known cache replacement policies to the problem of online process discovery. The approach has been implemented in .NET, experimentally integrated with the Minit process mining tool and comparatively evaluated against an existing baseline using real-life datasets.

Are you ready to compete as intelligent technology meets human ingenuity to create the future workforce? Ryan Shanks from Accenture has some recommendations. A recent Accenture Strategy report, Reworking the Revolution: Are you ready to compete as intelligent technology meets human ingenuity to create the future workforce?, estimates that if businesses invest in artificial intelligence (AI) and human-machine collaboration at the same rate as top-performing companies, they could boost revenues by 38pc by 2022 and raise employment levels by 10pc. Collectively, this would lift profits by $4.8trn globally over the same period. For the average S&P 500 company, this equates to $7.5bn of revenues and a $880m lift to profitability.

The fast-moving field of artificial intelligence development is a lucrative one -- a head-spinning one -- an oft-surprising and exciting one. But peer past the frenzy of media headlines announcing the latest discoveries and newest breakthroughs and it's sad but true, the world of science, including technology, is a field dominated by godless leftists, too. Look at this headline, from a New Yorker piece in September of 2015: "All Scientists Should be Militant Atheists." That was by cosmologist Lawrence Krauss, who also served as the director of the Origins Project at Arizona State University, an endeavor aimed at exploring the universe, humanity and technology. Krauss saw his career suffer a bit of a hit in 2018, on the heels of accusations by women of sexual harassment -- accusations which he has strenuously denied, by the way.

AI Clouds: Lego blocking cloud based services with developer kits, large general purpose AI companies are enabling developers to deploy algorithms via SDKs within their cloud hosted platforms. From Microsoft Azure AI platform all the way to Amazon's AWS AI Offerings, these organizations provide pre-trained models, GPUs and storage that are necessary for more effective continuous deployment, testing and quality assurance (QA). AI Languages: Beyond software applications to onboard users onto AI platforms, companies are standardizing new languages to familiarize developers to continually build using their libraries. Uber's AI Labs, for example, released their own probabilistic python offshoot programming language, Pyro. Wit.ai is another language for developers to build cross device applications.

What do animals and galaxies have in common? The similarity is now helping conservationists monitor endangered animals that are often targeted by poachers. By deploying small drones with infrared cameras attached, scientists are developing tools for wildlife officials to watch these wild animals without disturbing them. At night, when poachers are most likely to strike, wildlife guards have a difficult time spotting animals in the dark. But on infrared cameras, they're impossible to miss.