The focus of the DeepMind paper concerns spatial reasoning, in particular the ability to grasp the relation of objects to each other. This may sound simple compared with becoming an expert in chess or the like. But it's only because humans possess something like an "intuitive physics engine," an algorithm for extrapolating three-dimensionality from flat images and comparing objects within it to other objects. This kind of spatial reasoning has proved difficult for computers, at least until now. Using a combination of relational networks and convoluted neural networks, the DeepMind system can answer questions concerning the relation of objects within an image.

Spatial Visualization Using R: One of the less understood aspects of R is in spatial data visualization. The below article will outline two case studies on using R to spatially visualize data. Our first step is figuring out how to use the Census API within R. Given below are the key data Source Details from the Census ACS Data We use the acs.lookup function & use the keywords to find the required data across all ACS tables. For example, the following are the search results for the keywords owner, occupied, and median. An object of class "acs.lookup"

Video sequences contain rich dynamic patterns, such as dynamic texture patterns that exhibit stationarity in the temporal domain, and action patterns that are non-stationary in either spatial or temporal domain. We show that a spatial-temporal generative ConvNet can be used to model and synthesize dynamic patterns. The model defines a probability distribution on the video sequence, and the log probability is defined by a spatial-temporal ConvNet that consists of multiple layers of spatial-temporal filters to capture spatial-temporal patterns of different scales. The model can be learned from the training video sequences by an "analysis by synthesis" learning algorithm that iterates the following two steps. Step 1 synthesizes video sequences from the currently learned model. Step 2 then updates the model parameters based on the difference between the synthesized video sequences and the observed training sequences. We show that the learning algorithm can synthesize realistic dynamic patterns.

Watching this week's I/O livestream I came away somewhat awestruck by Google's vision. Gone are the days of talking about tablets and phones. I hope I'm not alone in feeling that this was one of the more complex keynotes at the annual conference for developers. A times it felt like sitting in on a first year university engineering class. The big picture seems to be either H.G. Wells utopia or Orwellian dystopia.

Several problems requiere the combination of temporal and spatial reasoning under uncertainty, such as wind prediction for electricity generation in wind farms. In this work we propose a probabilistic spatial-temporal model (PSTM) focused on prediction problems, based on two common properties of these scenarios: sparsity and multivariable mutual information. The proposed spatial-temporal model is essentially a Bayesian network that represents the dependencies between a target variable of interest and a subset of predictor variables in different times and spaces. We developed an algorithm for learning the structure of the model based on a stochastic search of the optimal subset of predictor variables. The proposed model has been applied for wind prediction at different locations in Mexico, using information from several locations at different times. The PSTM is evaluated in terms of predictive accuracy for different time horizons — 1 to 24 hours; and compared to a dynamic Bayesian network (DBN) developed for wind prediction. The performance of the PSTM is in general competitive, and in most cases superior to the DBN.

This paper introduces and discusses a new algebraic structure, the quasi-topologic structure. The idea of this structure comes from language analysis on the one hand and from analysis of some real situations of clustering on the other. From the cognitive point of view, it is related to the Logic of Determination of Objects (LDO) and to the Logic of Typical and Atypical Objects (LTA) which is particular case of LDO. From the mathematical point of view, it is related to topology. By introducing the notion of internal and external border, it extends the notion of border from classical topology.

People can upload a geotagged video, photo or text to social networks like Facebook and Twitter, share their present location on Foursquare or share their travel route using GPS trajectories to GeoLife [49]. A considerable amount of this spatiotemporal data is generated by the activity of users in location-based social networks (LBSN). In a typical LBSN, like Foursquare, users share the time and geolocation of their check-ins, comment about it, or unlock badges by exploring new venues. Many techniques have been proposed for processing, managing, and mining the trajectory data in the past decade [55]. Several other studies try to leverage the spatial data in recommender systems [23]. However, a few works have attempted to model the spatiotemporal behavior of users in LBSNs [5, 6]. Given the history of users' check-ins, the goal is to predict the time and location of This work is supported by ICT Innovation Center, Department of Computer Engineering, Sharif University of Technology, Tehran, Iran. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page.

Poaching is considered a major driver for the population drop of key species such as tigers, elephants, and rhinos, which can be detrimental to whole ecosystems. While conducting foot patrols is the most commonly used approach in many countries to prevent poaching, such patrols often do not make the best use of the limited patrolling resources.

We are adding python integration that enables advanced users and data scientists to call on python scripts from within the Tableau calculation window. Customers can use this functionality to develop advanced-analytics applications, and visualize their predictive models from Python in Tableau. Enabling customers to leverage their spatial data directly in Tableau for easy geospatial analysis. One customer is excited to use this for shape files generated from a customer clustering study, along with census data. With 10.2, we now have over 60 native data connectors.

Fine-grained image classification is challenging due to the large intra-class variance and small inter-class variance, aiming at recognizing hundreds of sub-categories belonging to the same basic-level category. Since two different sub-categories is distinguished only by the subtle differences in some specific parts, semantic part localization is crucial for fine-grained image classification. Most previous works improve the accuracy by looking for the semantic parts, but rely heavily upon the use of the object or part annotations of images whose labeling are costly. Recently, some researchers begin to focus on recognizing sub-categories via weakly supervised part detection instead of using the expensive annotations. However, these works ignore the spatial relationship between the object and its parts as well as the interaction of the parts, both of them are helpful to promote part selection. Therefore, this paper proposes a weakly supervised part selection method with spatial constraints for fine-grained image classification, which is free of using any bounding box or part annotations. We first learn a whole-object detector automatically to localize the object through jointly using saliency extraction and co-segmentation. Then two spatial constraints are proposed to select the distinguished parts. The first spatial constraint, called box constraint, defines the relationship between the object and its parts, and aims to ensure that the selected parts are definitely located in the object region, and have the largest overlap with the object region. The second spatial constraint, called parts constraint, defines the relationship of the object's parts, is to reduce the parts' overlap with each other to avoid the information redundancy and ensure the selected parts are the most distinguishing parts from other categories. Combining two spatial constraints promotes parts selection significantly as well as achieves a notable improvement on fine-grained image classification. Experimental results on CUB-200-2011 dataset demonstrate the superiority of our method even compared with those methods using expensive annotations.