scholarly journals Generalisation Enhancement via Input Space Transformation: A GP Approach

2014 ◽  
pp. 61-74 ◽  
Author(s):  
Ahmed Kattan ◽  
Michael Kampouridis ◽  
Alexandros Agapitos
Keyword(s):  
Input Space ◽  
Space Transformation

Color Space Transformation using Neural Networks

2019 ◽  
Vol 2019 (1) ◽  
pp. 153-158
Author(s):  
Lindsay MacDonald
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Color Space ◽  
Reflectance Spectra ◽  
Network Architectures ◽  
Color Spaces ◽  
Natural Materials ◽  
Space Transformation ◽  
Color Space Transformation

We investigated how well a multilayer neural network could implement the mapping between two trichromatic color spaces, specifically from camera R,G,B to tristimulus X,Y,Z. For training the network, a set of 800,000 synthetic reflectance spectra was generated. For testing the network, a set of 8,714 real reflectance spectra was collated from instrumental measurements on textiles, paints and natural materials. Various network architectures were tested, with both linear and sigmoidal activations. Results show that over 85% of all test samples had color errors of less than 1.0 ΔE2000 units, much more accurate than could be achieved by regression.

A Correspondence-Free Color Chart Design for Color Calibration

2020 ◽  
Vol 2020 (1) ◽  
pp. 100-104
Author(s):  
Hakki Can Karaimer ◽  
Rang Nguyen
Keyword(s):  
Color Space ◽  
Fixed Number ◽  
New Approach ◽  
Color Chart ◽  
Color Calibration ◽  
Space Transformation ◽  
Color Space Transformation ◽  
Chart Design ◽  
Calibration Approach

Colorimetric calibration computes the necessary color space transformation to map a camera's device-specific color space to a device-independent perceptual color space. Color calibration is most commonly performed by imaging a color rendition chart with a fixed number of color patches with known colorimetric values (e. g., CIE XYZ values). The color space transformation is estimated based on the correspondences between the camera's image and the chart's colors. We present a new approach to colorimetric calibration that does not require explicit color correspondences. Our approach computes a color space transformation by aligning the color distributions of the captured image to the known distribution of a calibration chart containing thousands of colors. We show that a histogram-based colorimetric calibration approach provides results that are onpar with the traditional patch-based method without the need to establish correspondences.

Inventing Synagogue Conversion

2013 ◽  
Vol 4 (3) ◽  
pp. 401-416
Author(s):  
Shira L. Lander
Keyword(s):  
Religious Belief ◽  
Sacred Space ◽  
Sixth Century ◽  
Building Structures ◽  
Late Antique ◽  
Complex Processes ◽  
Space Transformation

Historians of the ancient synagogue often use the term “conversion” to describe any kind of adaptation of a building once designated as a synagogue into a church. This label oversimplifies and misconstrues complex processes, both rhetorical and architectural, that were at work in transforming the landscape of the late antique Mediterranean. I explore the dynamic of this triumphalist rhetoric and architectural strategy, showing that Christian writers meant something very specific by the term “conversion,” and that they invented the paradigm of synagogue conversion in order to interpret the changing landscape to their readers. The architectural program of replacement as a strategy for converting subject populations to Christianity emerged in the sixth century. By characterizing changes made to building structures and changes in religious belief as “conversion,” imperial policy concretized the association of sacred space transformation with the victory of Christianity over Judaism and paganism.

scholarly journals gbt-HIPS: Explaining the Classifications of Gradient Boosted Tree Ensembles

2021 ◽  
Vol 11 (6) ◽  
pp. 2511
Author(s):  
Julian Hatwell ◽  
Mohamed Medhat Gaber ◽  
R. Muhammad Atif Azad
Keyword(s):  
State Of The Art ◽  
Heuristic Method ◽  
Good Explanation ◽  
Classification Rule ◽  
Data Sets ◽  
Classification Models ◽  
Boundary Values ◽  
Class Label ◽  
Input Space ◽  
Boosted Tree

This research presents Gradient Boosted Tree High Importance Path Snippets (gbt-HIPS), a novel, heuristic method for explaining gradient boosted tree (GBT) classification models by extracting a single classification rule (CR) from the ensemble of decision trees that make up the GBT model. This CR contains the most statistically important boundary values of the input space as antecedent terms. The CR represents a hyper-rectangle of the input space inside which the GBT model is, very reliably, classifying all instances with the same class label as the explanandum instance. In a benchmark test using nine data sets and five competing state-of-the-art methods, gbt-HIPS offered the best trade-off between coverage (0.16–0.75) and precision (0.85–0.98). Unlike competing methods, gbt-HIPS is also demonstrably guarded against under- and over-fitting. A further distinguishing feature of our method is that, unlike much prior work, our explanations also provide counterfactual detail in accordance with widely accepted recommendations for what makes a good explanation.

scholarly journals A sparse iteration space transformation framework for sparse tensor algebra

2020 ◽  
Vol 4 (OOPSLA) ◽  
pp. 1-30 ◽  
Author(s):  
Ryan Senanayake ◽  
Changwan Hong ◽  
Ziheng Wang ◽  
Amalee Wilson ◽  
Stephen Chou ◽  
...  
Keyword(s):  
Tensor Algebra ◽  
Iteration Space ◽  
Space Transformation
Sign in / Sign up

Export Citation Format

Share Document