An Intrusion Detection System (IDS) is a key cybersecurity tool for network administrators as it identifies malicious traffic and cyberattacks. With the recent successes of machine learning techniques such as deep learning, more and more IDS are now using machine learning algorithms to detect attacks faster. However, these systems lack robustness when facing previously unseen types of attacks. With the increasing number of new attacks, especially against Internet of Things devices, having a robust IDS able to spot unusual and new attacks becomes necessary. This work explores the possibility of leveraging generative adversarial models to improve the robustness of machine learning based IDS. More specifically, we propose a new method named SIGMA, that leverages adversarial examples to strengthen IDS against new types of attacks. Using Generative Adversarial Networks (GAN) and metaheuristics, SIGMA %Our method consists in generates adversarial examples, iteratively, and uses it to retrain a machine learning-based IDS, until a convergence of the detection rate (i.e. until the detection system is not improving anymore). A round of improvement consists of a generative phase, in which we use GANs and metaheuristics to generate instances ; an evaluation phase in which we calculate the detection rate of those newly generated attacks ; and a training phase, in which we train the IDS with those attacks. We have evaluated the SIGMA method for four standard machine learning classification algorithms acting as IDS, with a combination of GAN and a hybrid local-search and genetic algorithm, to generate new datasets of attacks. Our results show that SIGMA can successfully generate adversarial attacks against different machine learning based IDS. Also, using SIGMA, we can improve the performance of an IDS to up to 100\% after as little as two rounds of improvement.

There has been considerable advance in understanding the properties of sparse regularization procedures in high-dimensional models. Most of the work is limited to either independent and identically distributed setting, or time series with independent and/or (sub-)Gaussian innovations. We extend current literature to a broader set of innovation processes, by assuming that the error process is non-sub-Gaussian and conditionally heteroscedastic, and the generating process is not necessarily sparse. This setting covers fat tailed, conditionally dependent innovations which is of particular interest for financial risk modeling. It covers several multivariate-GARCH specifications, such as the BEKK model, and other factor stochastic volatility specifications.

This work presents an analysis of the discriminators used in Generative Adversarial Networks (GANs) for Video. We show that unconstrained video discriminator architectures induce a loss surface with high curvature which make optimisation difficult. We also show that this curvature becomes more extreme as the maximal kernel dimension of video discriminators increases. With these observations in hand, we propose a family of efficient Lower-Dimensional Video Discriminators for GANs (LDVD GANs). The proposed family of discriminators improve the performance of video GAN models they are applied to and demonstrate good performance on complex and diverse datasets such as UCF-101. In particular, we show that they can double the performance of Temporal-GANs and provide for state-of-the-art performance on a single GPU.

Mean field games (MFG) and mean field control (MFC) are critical classes of multi-agent models for efficient analysis of massive populations of interacting agents. Their areas of application span topics in economics, finance, game theory, industrial engineering, crowd motion, and more. In this paper, we provide a flexible machine learning framework for the numerical solution of potential MFG and MFC models. State-of-the-art numerical methods for solving such problems utilize spatial discretization that leads to a curse-of-dimensionality. We approximately solve high-dimensional problems by combining Lagrangian and Eulerian viewpoints and leveraging recent advances from machine learning. More precisely, we work with a Lagrangian formulation of the problem and enforce the underlying Hamilton-Jacobi-Bellman (HJB) equation that is derived from the Eulerian formulation. Finally, a tailored neural network parameterization of the MFG/MFC solution helps us avoid any spatial discretization. Our numerical results include the approximate solution of 100-dimensional instances of optimal transport and crowd motion problems on a standard work station. These results open the door to much-anticipated applications of MFG and MFC models that were beyond reach with existing numerical methods.

A classic graph coloring problem is to assign colors to vertices of any graph so that distinct colors are assigned to adjacent vertices. Optimal graph coloring colors a graph with a minimum number of colors, which is its chromatic number . Finding out the chromatic number is a combinatorial optimization problem proven to be computationally intractable, which implies that no algorithm that computes large instances of the problem in a reasonable time is known. F or this reason, approximate methods and metaheuristics form a set of techniques that do not guarantee optimality, but obtain good solutions in a reasonable time. This paper reports a comparative study of the Hill-Climbing, Simulated Annealing, T abu Search, and Iterated Local Search metaheuristics for the classic graph coloring problem considering its time efficiency for processing the DSJC125 and DSJC250 instances of the DIMACS benchmark.

Was investigated in this paper the use of a search strategy in the problem of finding the best path among multiple origins and multiple destinations. In this kind of problem, it must be decided within a lot of combinations which is the best origin and the best destination, and also the best path between these two regions. One remarkable difficulty to answer this sort of problem is to perform the search in a reduced time. This monography is a extension of previous research in which the problem described here was studied only in a bus network in the city of Fortaleza. This extension consisted of an exploration of the search strategy in graphs that represent public ways in cities like Fortaleza, Mumbai and Tokyo. Using this strategy with a heuristic algorithm, Haversine distance, was noticed that is possible to reduce substantially the time of the search, but introducing an error because of the loss of the admissible characteristic of the heuristic function applied.

In this paper, we present our position for a neural - symbolic integration strategy, arguing in favor of a hybrid representation to promote an effective integration. Such description differs from others fundamentally, since its entities aim at repre senting AI models in general, allowing to describe both non - symbolic and symbolic knowledge, the integration between them and their corresponding processors. Moreover, the entities also support representing workflows, leveraging traceability to keep track of every change applied to models and their related entities (e.g., data or concepts) throughout the lifecycle of the models.

SAN FRANCISCO, Dec. 17, 2019 (GLOBE NEWSWIRE) -- Holberton School, the two-year tuition-deferred college alternative educating the next generation of digital workers, announced the launch of their brand new Machine Learning curriculum which will be available at all eight world-wide Holberton campuses. The announcement was made at the flagship San Francisco campus featuring Grammy award-winner NE-YO, Black Girls Code founder and CEO Kimberly Bryant and representatives from Google (Tensorflow) and IBM. "Machine Learning, and by extension Artificial Intelligence, are increasingly dominating how we interact with technology at all levels, and the need for diversity has never been so urgent," said Gabriela de Queiroz, founder, AI Inclusive and R-Ladies. "Having programming skills isn't enough -- we need people who are aware of the ethical implications of AI, who can bring their diverse backgrounds, experiences, and perspectives to the workplace and incorporate them into the algorithms that will increasingly play a major role in healthcare, safety, and every other element of our lives." Machine Learning, which gives computers the capability to learn without being explicitly programmed, is already in use across the globe and is rapidly supplementing, and even replacing, traditional software development.

Climate change activist Greta Thunberg has been named one of the ten most influential people in science in 2019 by the journal Nature. The 16 year old has been named alongside a neurologist who brought pig brains back to life and a palaeontologist who shook up humanity's family tree. The prestigious British science journal, which celebrated its 150th anniversary this year, says the Swedish campaigner'channelled the rage of a generation'. She had outshone scientists who couldn't'galvanise global attention' the way she did and many are cheering her along, according to Nature. The ten most influential list also includes a physicist building quantum computers, a biologist editing genes in adult humans and a microbiologist fighting Ebola.

The US government must spend $25 billion on artificial intelligence research by 2025, stem the loss of foreign AI talent, and find new ways to prevent critical AI technology from being stolen and exported, according to a policy report issued Tuesday. Otherwise it risks falling behind China and losing its standing on the world stage. The report, from the Center for New American Security (CNAS), is the latest to highlight the importance of AI to the future of the US. It argues that the technology will define economic, military, and geopolitical power in coming decades. Advanced technologies, including AI, 5G wireless services, and quantum computing, are already at the center of an emerging technological cold war between the US and China. The Trump administration has declared AI a national priority, and it has enacted policies, such as technology export controls, designed to limit China's progress in AI and related areas.