Fortnite has hit 125 million players worldwide just a year after it was first released. The unrivaled popularity of Fortnite among players has partly been fueled by its availability for free on smartphones as well as on traditional home video game consoles, making it popular among teenage gamers as well as seasoned players. Its recent rise has already prompted a reaction from established gaming giants, with the next Call of Duty game – Black Ops 4 – removing its regular single player campaign mode for a Fortnite-style battle royale feature instead. Studio Epic Games, the creator of the free-to-play multiplayer game, also announced more details for the upcoming 2018-2019 competitive season. Fortnite is one of the most popular video games in the world, attracting more than 40 million players worldwide to its battle royale-style tournaments.

South African-based data scientists at Principa are at it again; this time using predictive analytics and machine learning to foretell the results of the 2018 Football World Cup. The 2018 FIFA World Cup kicks off tomorrow in Russia with the host nation taking on Saudi Arabia in Group A. Principa has already predicted the results for all the first games in the first round of matches. The company's data scientists use different algorithms to develop models that can predict the outcome of the matches. Principa notes that as the objective of machine learning is to develop models that can retrain themselves to adapt when exposed to new data, the algorithms will be re-trained with the results of each match to improve the accuracy of the following round's generated prediction. It points out that the purpose is to see how well different predictive analytics techniques used successfully in other areas can outperform the best human-made predictions.

The longevity and biotechnology industries are focusing on aging in a big way, and it's beginning to show. The fields of Artificial Intelligence (AI) and regenerative medicine are putting their money on combating aging and age-related diseases, and the benefits are likely to be immense. While biotechnology and AI are relatively new concepts, the announcements of funding and collaboration yesterday by and between three companies are bringing those concepts that much closer to the forefront of medicine. Insilico Medicine, a Baltimore-based next-generation AI company specializing in the application of deep learning for target identification, drug discovery and aging research, yesterday announced a collaboration agreement with WuXi AppTec, a leading global contract research outsourcing provider based in Shanghai, China, serving the pharmaceutical, biotech, and medical device industries. "It's a big step not only for Insilico Medicine but for AI and the pharmaceutical industries," said Alex Zhavoronkov, PhD, CEO of Insilico Medicine, Inc.

In the past few years, Convolutional Neural Networks (CNNs) have been achieving state-of-the-art performance on a variety of problems. Many companies employ resources and money to generate these models and provide them as an API, therefore it is in their best interest to protect them, i.e., to avoid that someone else copies them. Recent studies revealed that state-of-the-art CNNs are vulnerable to adversarial examples attacks, and this weakness indicates that CNNs do not need to operate in the problem domain (PD). Therefore, we hypothesize that they also do not need to be trained with examples of the PD in order to operate in it. Given these facts, in this paper, we investigate if a target black-box CNN can be copied by persuading it to confess its knowledge through random non-labeled data. The copy is two-fold: i) the target network is queried with random data and its predictions are used to create a fake dataset with the knowledge of the network; and ii) a copycat network is trained with the fake dataset and should be able to achieve similar performance as the target network. This hypothesis was evaluated locally in three problems (facial expression, object, and crosswalk classification) and against a cloud-based API. In the copy attacks, images from both non-problem domain and PD were used. All copycat networks achieved at least 93.7% of the performance of the original models with non-problem domain data, and at least 98.6% using additional data from the PD. Additionally, the copycat CNN successfully copied at least 97.3% of the performance of the Microsoft Azure Emotion API. Our results show that it is possible to create a copycat CNN by simply querying a target network as black-box with random non-labeled data.

Heuristic tools from statistical physics have been used in the past to locate the phase transitions and compute the optimal learning and generalization errors in the teacher-student scenario in multi-layer neural networks. In this contribution, we provide a rigorous justification of these approaches for a two-layers neural network model called the committee machine. We also introduce a version of the approximate message passing (AMP) algorithm for the committee machine that allows to perform optimal learning in polynomial time for a large set of parameters. We find that there are regimes in which a low generalization error is information-theoretically achievable while the AMP algorithm fails to deliver it, strongly suggesting that no efficient algorithm exists for those cases, and unveiling a large computational gap.

We consider the problem of learning a realization for a linear time-invariant (LTI) dynamical system from input/output data. Given a single input/output trajectory, we provide finite time analysis for learning the system's Markov parameters, from which a balanced realization is obtained using the classical Ho-Kalman algorithm. By proving a stability result for the Ho-Kalman algorithm and combining it with the sample complexity results for Markov parameters, we show how much data is needed to learn a balanced realization of the system up to a desired accuracy with high probability.

Automated service classification plays a crucial role in service management such as service discovery, selection, and composition. In recent years, machine learning techniques have been used for service classification. However, they can only predict around 10 to 20 service categories due to the quality of feature engineering and the imbalance problem of service dataset. In this paper, we present a deep neural network ServeNet with a novel dataset splitting algorithm to deal with these issues. ServeNet can automatically abstract low-level representation to high-level features, and then predict service classification based on the service datasets produced by the proposed splitting algorithm. To demonstrate the effectiveness of our approach, we conducted a comprehensive experimental study on 10,000 real-world services in 50 categories. The result shows that ServeNet can achieve higher accuracy than other machine learning methods.

Cultural activity is an inherent aspect of urban life and the success of a modern city is largely determined by its capacity to offer generous cultural entertainment to its citizens. To this end, the optimal allocation of cultural establishments and related resources across urban regions becomes of vital importance, as it can reduce financial costs in terms of planning and improve quality of life in the city, more generally. In this paper, we make use of a large longitudinal dataset of user location check-ins from the online social network WeChat to develop a data-driven framework for cultural planning in the city of Beijing. We exploit rich spatio-temporal representations on user activity at cultural venues and use a novel extended version of the traditional latent Dirichlet allocation model that incorporates temporal information to identify latent patterns of urban cultural interactions. Using the characteristic typologies of mobile user cultural activities emitted by the model, we determine the levels of demand for different types of cultural resources across urban areas. We then compare those with the corresponding levels of supply as driven by the presence and spatial reach of cultural venues in local areas to obtain high resolution maps that indicate urban regions with lack of cultural resources, and thus give suggestions for further urban cultural planning and investment optimisation.

Recurrent neural networks have gained widespread use in modeling sequence data across various domains. While many successful recurrent architectures employ a notion of gating, the exact mechanism that enables such remarkable performance is not well understood. We develop a theory for signal propagation in recurrent networks after random initialization using a combination of mean field theory and random matrix theory. To simplify our discussion, we introduce a new RNN cell with a simple gating mechanism that we call the minimalRNN and compare it with vanilla RNNs. Our theory allows us to define a maximum timescale over which RNNs can remember an input. We show that this theory predicts trainability for both recurrent architectures. We show that gated recurrent networks feature a much broader, more robust, trainable region than vanilla RNNs, which corroborates recent experimental findings. Finally, we develop a closed-form critical initialization scheme that achieves dynamical isometry in both vanilla RNNs and minimalRNNs. We show that this results in significantly improvement in training dynamics. Finally, we demonstrate that the minimalRNN achieves comparable performance to its more complex counterparts, such as LSTMs or GRUs, on a language modeling task.

Abstract--Modern data introduces new challenges to classic signal processing approaches, leading to a growing interest in the field of graph signal processing. A powerful and well established model for real world signals in various domains is sparse representation over a dictionary, combined with the ability to train the dictionary from signal examples. This model has been successfully applied to graph signals as well by integrating the underlying graph topology into the learned dictionary. Nonetheless, dictionary learning methods for graph signals are typically restricted to small dimensions due to the computational constraints that the dictionary learning problem entails, and due to the direct use of the graph Laplacian matrix. In this paper, we propose a dictionary learning algorithm that applies to a broader class of graph signals, and is capable of handling much higher dimensional data. We incorporate the underlying graph topology both implicitly, by forcing the learned dictionary atoms to be sparse combinations of graph-wavelet functions, and explicitly, by adding direct graph constraints to promote smoothness in both the feature and manifold domains. The resulting atoms are thus adapted to the data of interest while adhering to the underlying graph structure and possessing a desired multi-scale property. Experimental results on several datasets, representing both synthetic and real network data of different nature, demonstrate the effectiveness of the proposed algorithm for graph signal processing even in high dimensions. In recent years, the field of graph signal processing has been gaining momentum. By merging concepts of spectral graph theory and harmonic analysis, it aims at extending classical signal processing approaches to signals having a complex and irregular underlying structure. Such signals emerge in numerous modern applications of diverse sources, such as transportation, energy, biological-, social-, and sensor-networks [1], [2].