In this paper we present a logical formalism for the treatment of pragmatic ambiguity in spatial expressions of the frontal axis (front/back). The ambiguity occurs because the same situation can be analyzed from different points of view. For this, we use frames of reference for the interpretation of front/back (intrinsic, extrinsic, deictic) together with formalisms of qualitative spatial reasoning.

The statistician George Box once wrote that "all models are wrong, but some are useful"; the same could be said for maps. In this talk, we'll discuss the problems that arise when creating 2-dimensional representations of our world. We'll then see how to create data-rich maps using Python, matplotlib, and the basemap toolkit. Maps have been such a mainstay of our lives for so long now that it's hard to imagine just how complex it is to create one. Keep in mind though, the earth is a 3-dimensional spherical object, so we're stuck with the problem of "projecting" the world onto a 2-dimensional surface.

We're looking for a machine learning expert to unleash the power of data with our customers. You'll be working closely with our partners and customers on the most exciting data projects: product recommender systems, IoT data analysis, segmenting user behaviour profiles with web analytics data, geo-spatial analysis with billions of datapoints and many more. You will be part of a growing and agile team that has accumulated expertise in, computer vision, recommender systems, NLP and predictive analytics across various business sectors including media, telecommunication, finance and e-commerce. Working closely together with our data engineers you will be helping us to build our next-generation machine learning products. To be successful, you will need advanced analytic skills to find relationships, models, and statistical associations between massive data sets.

Topological Data Analysis (tda) is a recent and fast growing eld providing a set of new topological and geometric tools to infer relevant features for possibly complex data. This paper is a brief introduction, through a few selected topics, to basic fundamental and practical aspects of tda for non experts. 1 Introduction and motivation Topological Data Analysis (tda) is a recent eld that emerged from various works in applied (algebraic) topology and computational geometry during the rst decade of the century. Although one can trace back geometric approaches for data analysis quite far in the past, tda really started as a eld with the pioneering works of Edelsbrunner et al. (2002) and Zomorodian and Carlsson (2005) in persistent homology and was popularized in a landmark paper in 2009 Carlsson (2009). tda is mainly motivated by the idea that topology and geometry provide a powerful approach to infer robust qualitative, and sometimes quantitative, information about the structure of data-see, e.g. Chazal (2017). tda aims at providing well-founded mathematical, statistical and algorithmic methods to infer, analyze and exploit the complex topological and geometric structures underlying data that are often represented as point clouds in Euclidean or more general metric spaces. During the last few years, a considerable eort has been made to provide robust and ecient data structures and algorithms for tda that are now implemented and available and easy to use through standard libraries such as the Gudhi library (C++ and Python) Maria et al. (2014) and its R software interface Fasy et al. (2014a). Although it is still rapidly evolving, tda now provides a set of mature and ecient tools that can be used in combination or complementary to other data sciences tools. The tdapipeline. tda has recently known developments in various directions and application elds. There now exist a large variety of methods inspired by topological and geometric approaches. Providing a complete overview of all these existing approaches is beyond the scope of this introductory survey. However, most of them rely on the following basic and standard pipeline that will serve as the backbone of this paper: 1. The input is assumed to be a nite set of points coming with a notion of distance-or similarity between them. This distance can be induced by the metric in the ambient space (e.g. the Euclidean metric when the data are embedded in R d) or come as an intrinsic metric dened by a pairwise distance matrix. The denition of the metric on the data is usually given as an input or guided by the application. It is however important to notice that the choice of the metric may be critical to reveal interesting topological and geometric features of the data.

We introduce the concept of community trees that summarizes topological structures within a network. A community tree is a tree structure representing clique communities from the clique percolation method (CPM). The community tree also generates a persistent diagram. Community trees and persistent diagrams reveal topological structures of the underlying networks and can be used as visualization tools. We study the stability of community trees and derive a quantity called the total star number (TSN) that presents an upper bound on the change of community trees. Our findings provide a topological interpretation for the stability of communities generated by the CPM.

From suggesting how many steps we should walk in a day, to predicting the future price of our home, machine learning (ML) is becoming an integral part of our lives. ML is a new approach to understanding our universe based on exposing data-driven relationships and predicting outcomes without empirical models. Here at Esri, we are focused on empowering our users to unlock the full potential of their data using The Science of Where. The intersection of GIS and ML is a new frontier for turning spatial data into deep spatial understanding, and there are so many ways to integrate these powerful technologies to answer seemingly unanswerable questions. We recently did an analysis to predict global seagrass occurrence by harnessing the commonly used ML libraries of sci-kit learn and spatial analysis power of ArcGIS.

Person Re-Identification (person re-id) is a crucial task as its applications in visual surveillance and human-computer interaction. In this work, we present a novel joint Spatial and Temporal Attention Pooling Network (ASTPN) for video-based person re-identification, which enables the feature extractor to be aware of the current input video sequences, in a way that interdependency from the matching items can directly influence the computation of each other's representation. Specifically, the spatial pooling layer is able to select regions from each frame, while the attention temporal pooling performed can select informative frames over the sequence, both pooling guided by the information from distance matching. Experiments are conduced on the iLIDS-VID, PRID-2011 and MARS datasets and the results demonstrate that this approach outperforms existing state-of-art methods. We also analyze how the joint pooling in both dimensions can boost the person re-id performance more effectively than using either of them separately.

This work is supported by Anaconda Inc., the Data Driven Discovery Initiative from the Moore Foundation, and NASA SBIR NNX16CG43P This work is a collaboration with Joris Van den Bossche. This blogpost builds on Joris's EuroSciPy talk (slides) on the same topic. You can also see Joris' blogpost on this same topic. Python's Geospatial stack is slow. Dask gives an additional 3-4x on a multi-core laptop.

Data comes in all shapes and sizes and often government data is geospatial in nature. Often times data science programs & tutorials ignore how to work with this rich data to make room for more advanced topics. Our MinneMUDAC competition heavily utilized geospatial data but was processed to provide students a more familiar format. But as good scientists, we should use primary sources of information as often as possible. Come to this talk to get a basic understanding of how to read, write, query and perform simple geospatial calculations on Minnesota Tax shapefiles with Python.

We propose a method for hand pose estimation based on a deep regressor trained on two different kinds of input. Raw depth data is fused with an intermediate representation in the form of a segmentation of the hand into parts. This intermediate representation contains important topological information and provides useful cues for reasoning about joint locations. The mapping from raw depth to segmentation maps is learned in a semi/weakly-supervised way from two different datasets: (i) a synthetic dataset created through a rendering pipeline including densely labeled ground truth (pixelwise segmentations); and (ii) a dataset with real images for which ground truth joint positions are available, but not dense segmentations. Loss for training on real images is generated from a patch-wise restoration process, which aligns tentative segmentation maps with a large dictionary of synthetic poses. The underlying premise is that the domain shift between synthetic and real data is smaller in the intermediate representation, where labels carry geometric and topological meaning, than in the raw input domain. Experiments on the NYU dataset show that the proposed training method decreases error on joints over direct regression of joints from depth data by 15.7%.