Robotics and supply chain automation company, GreyOrange, will launch its new goods-to-person Butler XL at LogiMat 2018, the 16th International Trade Fair for Intralogistics Solutions and Process Management in Stuttgart, Germany on 13-15 March. With the new ButlerTM XL, GreyOrange expands the range of goods-to-person solutions that can be used in manufacturing facilities and omnichannel warehouses, to move different kinds of loads from raw materials to finished goods. The Butler XL can handle a payload of 1600 kgs (3500 lbs) including pallets, drums and sacks. Designed to work in tandem with the current Butler system, this makes it easy to add its new capabilities to existing operations. The new Butler robotics system will support multi-floor operations with the integration of an elevator.

Autonomous weapons are currently at the core of the debate about the future of artificial intelligence, and some countries are already starting to distance themselves from the ethical dilemma and the political controversy involved in their use. In a recent meeting of the United Nations' Convention on Conventional Weapons (CCW), world leaders have considered a possible ban on these so-called "killer robots" -- technically a misnomer, as these autonomous weapons aren't limited to just the robotic type. Now, at the annual Munich Security Conference (MSC), Germany made it clear they're not interested in developing autonomous weapon systems. "We have a very clear position. We have no intention of procuring […] autonomous systems," said Lieutenant General Ludwig Leinhos, head of Germany's new Cyber and Information Space Command, according to eNCA.

Recently, I reached out to 17 thought leaders -- AI experts, computer engineers, roboticists, physicists, and social scientists -- with a single question: "How worried should we be about artificial intelligence?" Disagreement about the appropriate level of concern, and even the nature of the problem, is broad. Some experts consider AI an urgent danger; many more believe the fears are either exaggerated or misplaced. Here is what they told me. I am infinitely excited about artificial intelligence and not worried at all.

In this paper we construct preimage attack on the truncated variant of the MD4 hash function. Specifically, we study the MD4-39 function defined by the first 39 steps of the MD4 algorithm. We suggest a new attack on MD4-39, which develops the ideas proposed by H. Dobbertin in 1998. Namely, the special relaxation constraints are introduced in order to simplify the equations corresponding to the problem of finding a preimage for an arbitrary MD4-39 hash value. The equations supplemented with the relaxation constraints are then reduced to the Boolean Satisfiability Problem (SAT) and solved using the state-of-the-art SAT solvers. We show that the effectiveness of a set of relaxation constraints can be evaluated using the black-box function of a special kind. Thus, we suggest automatic method of relaxation constraints generation by applying the black-box optimization to this function. The proposed method made it possible to find new relaxation constraints that contribute to a SAT-based preimage attack on MD4-39 which significantly outperforms the competition.

Social network analysis provides meaningful information about behavior of network members that can be used for diverse applications such as classification, link prediction. However, network analysis is computationally expensive because of feature learning for different applications. In recent years, many researches have focused on feature learning methods in social networks. Network embedding represents the network in a lower dimensional representation space with the same properties which presents a compressed representation of the network. In this paper, we introduce a novel algorithm named "CARE" for network embedding that can be used for different types of networks including weighted, directed and complex. Current methods try to preserve local neighborhood information of nodes, whereas the proposed method utilizes local neighborhood and community information of network nodes to cover both local and global structure of social networks. CARE builds customized paths, which are consisted of local and global structure of network nodes, as a basis for network embedding and uses the Skip-gram model to learn representation vector of nodes. Subsequently, stochastic gradient descent is applied to optimize our objective function and learn the final representation of nodes. Our method can be scalable when new nodes are appended to network without information loss. Parallelize generation of customized random walks is also used for speeding up CARE. We evaluate the performance of CARE on multi label classification and link prediction tasks. Experimental results on various networks indicate that the proposed method outperforms others in both Micro and Macro-f1 measures for different size of training data.

Contrary to the problem of detection, in which a decision is to be made about the presence or absence of a pattern, the problem of localization assumes that the pattern is present and its precise location is to be retrieved. The temporal nature of the data acquisition process complicates these tasks, as it causes the shape of the patterns of interest to suffer deformations in time known as warps. For pattern detection problems, many techniques exist based on aligning the query time series to a known reference pattern, commonly through dynamic time warping (DTW) [5]. Similarly, a common pattern localization technique consists in aligning the query time series to a reference time series that contains several patterns of interest [3]. The work of Steven Van Vaerenbergh was supported by the Ministerio de Economía, Industria y Competitividad (MINECO) of Spain under grant TEC2014-57402-JIN (PRISMA). The work of Víctor Elvira was supported by the Agence Nationale de la Recherche of France under PISCES project (ANR-17-CE40-0031-01).

There is a rising interest in studying the robustness of deep neural network classifiers against adversaries, with both advanced attack and defence techniques being actively developed. However, most recent work focuses on discriminative classifiers which only models the conditional distribution of the labels given the inputs. In this abstract we propose deep Bayes classifier that improves the classical naive Bayes with conditional deep generative models, and verifies its robustness against a number of existing attacks. We further developed a detection method for adversarial examples based on conditional deep generative models. Our initial results on MNIST suggest that deep Bayes classifiers might be more robust when compared with deep discriminative classifiers, and the proposed detection method achieves high detection rates against two commonly used attacks.

Gradient-based meta-learning has been shown to be expressive enough to approximate any learning algorithm. While previous such methods have been successful in meta-learning tasks, they resort to simple gradient descent during meta-testing. Our primary contribution is the {\em MT-net}, which enables the meta-learner to learn on each layer's activation space a subspace that the task-specific learner performs gradient descent on. Additionally, a task-specific learner of an {\em MT-net} performs gradient descent with respect to a meta-learned distance metric, which warps the activation space to be more sensitive to task identity. We demonstrate that the dimension of this learned subspace reflects the complexity of the task-specific learner's adaptation task, and also that our model is less sensitive to the choice of initial learning rates than previous gradient-based meta-learning methods. Our method achieves state-of-the-art or comparable performance on few-shot classification and regression tasks.

We study the problem of recovery of matrices that are simultaneously low rank and row and/or column sparse. Such matrices appear in recent applications in cognitive neuroscience, imaging, computer vision, macroeconomics, and genetics. We propose a GDT (Gradient Descent with hard Thresholding) algorithm to efficiently recover matrices with such structure, by minimizing a bi-convex function over a nonconvex set of constraints. We show linear convergence of the iterates obtained by GDT to a region within statistical error of an optimal solution. As an application of our method, we consider multi-task learning problems and show that the statistical error rate obtained by GDT is near optimal compared to minimax rate. Experiments demonstrate competitive performance and much faster running speed compared to existing methods, on both simulations and real data sets.

Networks are a fundamental model of complex systems throughout the sciences, and network datasets are typically analyzed through lower-order connectivity patterns described at the level of individual nodes and edges. However, higher-order connectivity patterns captured by small subgraphs, also called network motifs, describe the fundamental structures that control and mediate the behavior of many complex systems. We develop three tools for network analysis that use higher-order connectivity patterns to gain new insights into network datasets: (1) a framework to cluster nodes into modules based on joint participation in network motifs; (2) a generalization of the clustering coefficient measurement to investigate higher-order closure patterns; and (3) a definition of network motifs for temporal networks and fast algorithms for counting them. Using these tools, we analyze data from biology, ecology, economics, neuroscience, online social networks, scientific collaborations, telecommunications, transportation, and the World Wide Web.