This article is about the cognitive science of visual art. Artists create physical artifacts (such as sculptures or paintings) which depict people, objects, and events. These depictions are usually stylized rather than photo-realistic. How is it that humans are able to understand and create stylized representations? Does this ability depend on general cognitive capacities or an evolutionary adaptation for art? What role is played by learning and culture? Machine Learning can shed light on these questions. It's possible to train convolutional neural networks (CNNs) to recognize objects without training them on any visual art. If such CNNs can generalize to visual art (by creating and understanding stylized representations), then CNNs provide a model for how humans could understand art without innate adaptations or cultural learning. I argue that Deep Dream and Style Transfer show that CNNs can create a basic form of visual art, and that humans could create art by similar processes. This suggests that artists make art by optimizing for effects on the human object-recognition system. Physical artifacts are optimized to evoke real-world objects for this system (e.g. to evoke people or landscapes) and to serve as superstimuli for this system.

Evidence often grounds temporal probabilistic relational models over time, which makes reasoning infeasible. To counteract groundings over time and to keep reasoning polynomial by restoring a lifted representation, we present temporal approximate merging (T AMe), which incorporates (i) clustering for grouping submodels as well as (ii) statistical significance checks to test the fitness of the clustering outcome. In exchange for faster runtimes, T AMe introduces a bounded error that becomes negligible over time. Empirical results show that T AMe significantly improves the runtime performance of inference, while keeping errors small. Introduction Temporal probabilistic relational models express relations between objects, modelling uncertainty as well as temporal aspects. Within one time step, a temporal model is considered static. Performing inference on such models requires algorithms to efficiently handle the temporal aspect to be able to efficiently answer queries. Reasoning in lifted representations has a complexity polynomial in domain sizes. But, models dissolve into ground instances through evidence, which no longer permits reasoning in polynomial time, making query answering infeasible for any reasoning algorithm, exact or approximate. Thus, a key challenge during inference in temporal models is to restore a lifted, i.e., non-grounded, representation. Therefore, we formulate and study the problem of keeping reasoning polynomial (KRP) in temporal models to tame the effect of evidence for efficient query answering. First-order probabilistic inference leverages the relational aspect of a static model, using representatives for groups of indistinguishable, known objects, also known as lifting (Poole 2003). Poole (2003) presents parametric factor graphs as relational models and proposes lifted variable elimination (L VE) as an exact inference algorithm on relational models.

Imitation learning trains a policy from expert demonstrations. Imitation learning approaches have been designed from various principles, such as behavioral cloning via supervised learning, apprenticeship learning via inverse reinforcement learning, and GAIL via generative adversarial learning. In this paper, we propose a framework to analyze the theoretical property of imitation learning approaches based on discrepancy propagation analysis. Under the infinite-horizon setting, the framework leads to the value discrepancy of behavioral cloning in an order of O((1-\gamma)^{-2}). We also show that the framework leads to the value discrepancy of GAIL in an order of O((1-\gamma)^{-1}). It implies that GAIL has less compounding errors than behavioral cloning, which is also verified empirically in this paper. To the best of our knowledge, we are the first one to analyze GAIL's performance theoretically. The above results indicate that the proposed framework is a general tool to analyze imitation learning approaches. We hope our theoretical results can provide insights for future improvements in imitation learning algorithms.

Many real-world multi-agent reinforcement learning applications require agents to communicate, assisted by a communication protocol. These applications face a common and critical issue of communication's limited bandwidth that constrains agents' ability to cooperate successfully. In this paper, rather than proposing a fixed communication protocol, we develop an Informative Multi-Agent Communication (IMAC) method to learn efficient communication protocols. Our contributions are threefold. First, we notice a fact that a limited bandwidth translates into a constraint on the communicated message entropy, thus paving the way of controlling the bandwidth. Second, we introduce a customized batch-norm layer, which controls the messages' entropy to simulate the limited bandwidth constraint. Third, we apply the information bottleneck method to discover the optimal communication protocol, which can satisfy a bandwidth constraint via training with the prior distribution in the method. To demonstrate the efficacy of our method, we conduct extensive experiments in various cooperative and competitive multi-agent tasks across two dimensions: the number of agents and different bandwidths. We show that IMAC converges fast, and leads to efficient communication among agents under the limited-bandwidth constraint as compared to many baseline methods.

Inferring missing edges in multi-relational knowledge graphs is a fundamental task in statistical relational learning. However, previous work has largely focused on the transductive relation prediction problem, where missing edges must be predicted for a single, fixed graph. In contrast, many real-world situations require relation prediction on dynamic or previously unseen knowledge graphs (e.g., for question answering, dialogue, or e-commerce applications). Here, we develop a novel graph neural network (GNN) architecture to perform inductive relation prediction and provide a systematic comparison between this GNN approach and a strong, rule-based baseline. Our results highlight the significant difficulty of inductive relational learning, compared to the transductive case, and offer a new challenging set of inductive benchmarks for knowledge graph completion.

In cooperative pathfinding problems, no-conflicts paths that bring several agents from their start location to their destination need to be planned. This problem can be efficiently solved by Multi-agent RRT*(MA-RRT*) algorithm, which offers better scalability than the classical algorithms, such as Optimal Anytime(OA), in sparse environments. However, the implementation of this algorithm in systems with limited memory is hindered because the number of nodes in the tree grows indefinitely as the paths get optimized. This paper proposes an improved version of MA-RRT*, called Multi-agent RRT* Fixed Node(MA-RRT*FN), which limits the number of nodes stored in the tree by removing the weak nodes which are not likely on the path reaching the goal. The results show that MA-RRT*FN performs close to MA-RRT* in terms of scalability and solution quality while the memory required is much lower and fixed.

Privacy advocates used Amazon's facial recognition to scan thousands of random faces around Capitol Hill in Washington DC to highlight the dangers of this technologies surveillance capabilities. While walking around, the team found the facial recognition successfully identified a congressman, but also claimed to spot Roy Orbison – an American singer who died in 1988. The demonstration was a message to Congress to ban the technology, there's no law preventing people from scanning your face without your consent anytime you step out in public. A small group of activists walked outside and inside Capitol Hill wearing hazmat suits and smartphones strapped to their heads on Thursday to protest the use of facial recognition on the public without consent. Using Rekognition, Amazon's commercially available facial recognition software, the activists scanned nearly 14,000 faces that they cross-checked with a database to see if anyone could be identified.

For more than 60 years, the Lawrence Livermore National Laboratory (LLNL) has applied science and technology to make the world a safer place. We have multiple openings for Postdoctoral Research Staff Members to engage in the research, design, and deployment of machine learning and statistical methods to solve important data and science problems stemming from the Laboratory's mission spaces. You will work as part of collaborative, multidisciplinary teams to support a variety of application areas (such as material science, high energy physics, predictive medicine, cybersecurity, climate modeling). These positions are in the Center for Applied Scientific Computing (CASC) Division within the Computation Directorate. Essential Duties - Research, design, implement, and apply a variety of advanced data science methods for multiple applications in a collaborative scientific environment.

To gauge the complexity of the juggling act utility firms must perform to stay in business, consider two statistics. In the four years to 2018, the number of Britons who switched their energy supplier almost doubled to 5.9 million; at the same time, the contribution of renewables to energy firms' output mix grew from about 13% to just shy of 20%. One represents a fundamental change in consumer expectations of the service they receive while the other highlights the political and environmental pressures being brought to bear on suppliers' operations. To the list of challenges that are adding to the pressures under which utilities operate, add the tightening – and disparate – the grip of regulators, the fracturing of transmission networks and the increasing influence of activist investors. Managing these changing times can be incredibly challenging for established utilities, especially at a time when technology is enabling venture-backed start-ups to move into niche segments of their operations.

For data-complex and risk-adverse industries like insurance, being able to access data locked away in file stores and data lakes is critical for effective decision making. Data collection and analysis is at the heart of insurance business processes. Real-time data extraction enables insurers to automate and standardize time-consuming labor-intensive processes. With insurers being under pressure to deliver a better customer experience, they are being forced to examine existing processes and adopt new methods of doing business. But given the plethora of technology available, it can be difficult to understand what it is and how to use it.