Spatial Reasoning


Origami anything

#artificialintelligence

At the Symposium on Computational Geometry in July, Demaine and Tomohiro Tachi of the University of Tokyo will announce the completion of a quest that began with that 1999 paper: a universal algorithm for folding origami shapes that guarantees a minimum number of seams. But if you were going to start with a square piece of paper, then that old method would basically fold the square paper down to a thin strip, wasting almost all the material. The researchers' algorithm designs crease patterns for producing any polyhedron -- that is, a 3-D surface made up of many flat facets. Along the way, there have been several nice demonstrations of pieces of the puzzle: an algorithm to fold any shape, but not very efficiently; an algorithm to efficiently fold particular families of tree-like shapes, but not surfaces; an algorithm to fold trees and surfaces, but not every shape.


AI Acquires Spatial Reasoning Abilities, in a Victory for Our Machine Overlords - ExtremeTech

#artificialintelligence

The focus of the DeepMind paper concerns spatial reasoning, in particular the ability to grasp the relation of objects to each other. 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.


R Spatial Representation

@machinelearnbot

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. The second case study is using Home Insurance Rates data by vHomeInsurance, and using GGMap, to show average home insurance prices for some of the most populated cities in the US. The map will show more expensive home insurance cities in bigger circles and less expensive cities in smaller circles.


The Big Value of Weather Data in the Big Data Economy

@machinelearnbot

According to The New York Times, while The Weather Company employs many atmospheric scientists and meteorologists, nearly three-quarters of its scientists work in data and computers. In fact, weather data is increasingly important in scores of industries to create accurate predictive models using machine learning algorithms. Technology companies and analytics vendors who can build accurate weather data into their predictive models could see a massive competitive advantage. As is often the case, combining IBM's analytics power and the weather data collected by The Weather Company will undoubtedly lead to more answers -- and more questions -- than we can accurately predict at this time.



How Encrypted Weather Data Could Help Corporate Blockchain Dreams Come True

MIT Technology Review

In the era of fake news, professor and cryptographer Ari Juels is preparing to launch an online service designed to provide the most trustworthy information on the Internet. The Town Crier service launching next week is designed to showcase software of the same name that Juels and colleagues at Cornell say offers a solution. The demonstration service launching next week will provide feeds of data including stock prices, weather reports, flight information, cryptocurrency exchange rates, and UPS package tracking. Town Crier's design also allows smart contracts to hide the data they are using from everyone but the parties to the contract.


[Report] Dengue diversity across spatial and temporal scales: Local structure and the effect of host population size

Science

A fundamental mystery for dengue and other infectious pathogens is how observed patterns of cases relate to actual chains of individual transmission events. Using geolocated genotype (800 cases) and serotype (17,291 cases) data, we show that in Bangkok, Thailand, 60% of dengue cases living 200 meters apart come from the same transmission chain, as opposed to 3% of cases separated by 1 to 5 kilometers. This trend is observed regardless of whether population density or area increases, though increases in density over 7000 people per square kilometer do not lead to additional chains. These findings are consistent with local, density-dependent transmission and implicate densely populated communities as key sources of viral diversity, with home location the focal point of transmission.


The Big Value of Weather Data in the Big Data Economy

@machinelearnbot

According to The New York Times, while The Weather Company employs many atmospheric scientists and meteorologists, nearly three-quarters of its scientists work in data and computers. In fact, weather data is increasingly important in scores of industries to create accurate predictive models using machine learning algorithms. Technology companies and analytics vendors who can build accurate weather data into their predictive models could see a massive competitive advantage. As is often the case, combining IBM's analytics power and the weather data collected by The Weather Company will undoubtedly lead to more answers -- and more questions -- than we can accurately predict at this time.


Descartes Labs opens its geospatial analysis engine to a handful of lucky developers

#artificialintelligence

Descartes Labs, a startup that combines satellite imagery with data about our planet to produce insights and forecasts, knows this all too well. The company ended up building its own cloud-based parallel computing infrastructure to clean and process its massive corpus of satellite imagery. Companies like Descartes Labs cannot just throw raw satellite imagery into machine learning models to extract insights. This is where Descartes Labs's processing engine comes into play to convert into composites the petabytes of geospatial data it has.


R Spatial Representation

@machinelearnbot

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. The second case study is using Home Insurance Rates data by vHomeInsurance, and using GGMap, to show average home insurance prices for some of the most populated cities in the US. The map will show more expensive home insurance cities in bigger circles and less expensive cities in smaller circles.