scholarly journals Bimodal Network Architectures for Automatic Generation of Image Annotation from Text

2018 ◽  
pp. 449-456 ◽  
Author(s):  
Mehdi Moradi ◽  
Ali Madani ◽  
Yaniv Gur ◽  
Yufan Guo ◽  
Tanveer Syeda-Mahmood
Keyword(s):  
Image Annotation ◽  
Automatic Generation ◽  
Network Architectures

scholarly journals Automatic Generation of Neural Networks

2009 ◽  
Vol 2 (1) ◽  
Author(s):  
A. Fiszelew ◽  
P. Britos ◽  
G. Perichisky ◽  
R. García-Martínez
Keyword(s):  
Back Propagation ◽  
Evaluation Criteria ◽  
Evolutionary Process ◽  
Automatic Generation ◽  
Network Architectures ◽  
Back Propagation Algorithm ◽  
Early Stopping ◽  
Domain Specific ◽  
Network Training ◽  
Complex Regulation

This work deals with methods for finding optimal neural network architectures to learn par-ticular problems. A genetic algorithm is used to discover suitable domain specific architectures; this evolutionary algorithm applies direct codification and uses the error from the trained network as a per-formance measure to guide the evolution. The network training is accomplished by the back-propagation algorithm; techniques such as training repetition, early stopping and complex regulation are employed to improve the evolutionary process results. The evaluation criteria are based on learn-ing skills and classification accuracy of generated architectures

The Role of Visual Distractors in the Simon Effect

2017 ◽  
Vol 64 (6) ◽  
pp. 387-397 ◽  
Author(s):  
Luisa Lugli ◽  
Stefania D’Ascenzo ◽  
Roberto Nicoletti ◽  
Carlo Umiltà
Keyword(s):  
Simon Effect ◽  
Simon Task ◽  
Automatic Generation ◽  
Spatial Code ◽  
Attentional Model ◽  
Previous Evidence ◽  
Spatial Stimulus ◽  
Attentional Resources ◽  
Code Changes

Abstract. The Simon effect lies on the automatic generation of a stimulus spatial code, which, however, is not relevant for performing the task. Results typically show faster performance when stimulus and response locations correspond, rather than when they do not. Considering reaction time distributions, two types of Simon effect have been individuated, which are thought to depend on different mechanisms: visuomotor activation versus cognitive translation of spatial codes. The present study aimed to investigate whether the presence of a distractor, which affects the allocation of attentional resources and, thus, the time needed to generate the spatial code, changes the nature of the Simon effect. In four experiments, we manipulated the presence and the characteristics of the distractor. Findings extend previous evidence regarding the distinction between visuomotor activation and cognitive translation of spatial stimulus codes in a Simon task. They are discussed with reference to the attentional model of the Simon effect.

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.

Deep Learning Approaches for Whiteboard Image Quality Enhancement

2019 ◽  
Vol 2019 (1) ◽  
pp. 360-368
Author(s):  
Mekides Assefa Abebe ◽  
Jon Yngve Hardeberg
Keyword(s):  
Deep Learning ◽  
Image Quality ◽  
Image Data ◽  
Quality Enhancement ◽  
Network Architectures ◽  
Learning Approaches ◽  
Data Set ◽  
Image Quality Enhancement ◽  
Processing Techniques ◽  
White Balancing

Different whiteboard image degradations highly reduce the legibility of pen-stroke content as well as the overall quality of the images. Consequently, different researchers addressed the problem through different image enhancement techniques. Most of the state-of-the-art approaches applied common image processing techniques such as background foreground segmentation, text extraction, contrast and color enhancements and white balancing. However, such types of conventional enhancement methods are incapable of recovering severely degraded pen-stroke contents and produce artifacts in the presence of complex pen-stroke illustrations. In order to surmount such problems, the authors have proposed a deep learning based solution. They have contributed a new whiteboard image data set and adopted two deep convolutional neural network architectures for whiteboard image quality enhancement applications. Their different evaluations of the trained models demonstrated their superior performances over the conventional methods.

A Method for Reliability Assessment of Spatial Plate Structures Through Automatic Generation of Ultimate Collapse Modes

1991 ◽  
Vol 1991 (170) ◽  
pp. 483-491 ◽  
Author(s):  
Hiroo Okada ◽  
Yoshisada Murotsu ◽  
Keiji Ueyama ◽  
Minoru Harada ◽  
Kazuya Kondo
Keyword(s):  
Reliability Assessment ◽  
Automatic Generation ◽  
Plate Structures

Automatic Generation of MCQS from Domain Ontology- A Survey

2018 ◽  
Vol 06 (06) ◽  
pp. 99-102
Author(s):  
Sahana Serin V. P. ◽  
Viji Rajendran V.
Keyword(s):  
Automatic Generation ◽  
Domain Ontology
Sign in / Sign up

Export Citation Format

Share Document