AAAI84-066.pdf

AAAI Conferences

We prove that the scale map of the.zero-crossings of almost all signals filtered by a gaussian of variable size determines the signal uniquely, up to a constant scaling.


Non-Gaussian information from weak lensing data via deep learning

arXiv.org Machine Learning

Weak lensing maps contain information beyond two-point statistics on small scales. Much recent work has tried to extract this information through a range of different observables or via nonlinear transformations of the lensing field. Here we train and apply a 2D convolutional neural network to simulated noiseless lensing maps covering 96 different cosmological models over a range of {$\Omega_m,\sigma_8$}. Using the area of the confidence contour in the {$\Omega_m,\sigma_8$} plane as a figure-of-merit, derived from simulated convergence maps smoothed on a scale of 1.0 arcmin, we show that the neural network yields $\approx 5 \times$ tighter constraints than the power spectrum, and $\approx 4 \times$ tighter than the lensing peaks. Such gains illustrate the extent to which weak lensing data encode cosmological information not accessible to the power spectrum or even non-Gaussian statistics such as lensing peaks.


Global Fitting of the Response Surface via Estimating Multiple Contours of a Simulator

arXiv.org Machine Learning

Computer simulators are nowadays widely used to understand complex physical systems in many areas such as aerospace, renewable energy, climate modeling, and manufacturing. One fundamental issue in the study of computer simulators is known as experimental design, that is, how to select the input settings where the computer simulator is run and the corresponding response is collected. Extra care should be taken in the selection process because computer simulators can be computationally expensive to run. The selection shall acknowledge and achieve the goal of the analysis. This article focuses on the goal of producing more accurate prediction which is important for risk assessment and decision making. We propose two new methods of design approaches that sequentially select input settings to achieve this goal. The approaches make novel applications of simultaneous and sequential contour estimations. Numerical examples are employed to demonstrate the effectiveness of the proposed approaches.


Logic and MRF Circuitry for Labeling Occluding and Thinline Visual Contours

Neural Information Processing Systems

This paper presents representation and logic for labeling contrast edges and ridges in visual scenes in terms of both surface occlusion (border ownership) and thinline objects. In natural scenes, thinline objects include sticksand wires, while in human graphical communication thinlines include connectors, dividers, and other abstract devices. Our analysis is directed at both natural and graphical domains. The basic problem is to formulate the logic of the interactions among local image events, specifically contrast edges, ridges, junctions, and alignment relations, such as to encode the natural constraints among these events in visual scenes. In a sparse heterogeneous Markov Random Field framework, we define a set of interpretation nodes and energy/potential functions among them. The minimum energy configuration found by Loopy Belief Propagation isshown to correspond to preferred human interpretation across a wide range of prototypical examples including important illusory contour figuressuch as the Kanizsa Triangle, as well as more difficult examples. Inpractical terms, the approach delivers correct interpretations of inherently ambiguous hand-drawn box-and-connector diagrams at low computational cost.


I tried contouring for the first time and it wasn't as hard as it looked

Mashable

For a beauty junkie, I shamefully have never given makeup contouring a shot for fear of looking like a walking plastic doll due to my less-than-deft blending skills. I've watched plenty of tutorials on YouTube and I also studied "clown contouring" when it was a thing last year, but it always seemed to require more effort that I was willing to put in. But celebrity tattoo artist Kat Von D's new contouring makeup range landed on my desk and I figured I had to jump on it to see how a noob would do. Von D's eponymous cosmetics line will launch in Singapore in July at Sephora, and I've heard from the great beauty grapevine that her contour palettes and lipsticks are expected to sell like hotcakes. The face contour palette comes with three light and three dark powder shades, and will suit several skin tones.