scholarly journals Masking of alphabetic character recognition by dynamic visual noise (DVN)

1969 ◽  
Vol 6 (2) ◽  
pp. 121-128 ◽  
Author(s):  
William R. Uttal
Author(s):  
BRENT FERGUSON ◽  
RANADHIR GHOSH ◽  
JOHN YEARWOOD

This paper reports on an experimental approach to find a modularized artificial neural network solution for the UCI letters recognition problem. Our experiments have been carried out in two parts. We investigate directed task decomposition using expert knowledge and clustering approaches to find the subtasks for the modules of the network. We next investigate processes to combine the modules effectively in a single decision process. After having found suitable modules through task decomposition we have found through further experimentation that when the modules are combined with decision tree supervision, their functional error is reduced significantly to improve their combination through the decision process that has been implemented as a small multilayered perceptron. The experiments conclude with a modularized neural network design for this classification problem that has increased learning and generalization characteristics. The test results for this network are markedly better than a single or stand alone network that has a fully connected topology.


2018 ◽  
Vol 09 (03) ◽  
pp. 209-224 ◽  
Author(s):  
Md. Hasan Hasnain Nashif ◽  
Md. Badrul Alam Miah ◽  
Ahsan Habib ◽  
Autish Chandra Moulik ◽  
Md. Shariful Islam ◽  
...  

Author(s):  
Kevin Dent

In two experiments participants retained a single color or a set of four spatial locations in memory. During a 5 s retention interval participants viewed either flickering dynamic visual noise or a static matrix pattern. In Experiment 1 memory was assessed using a recognition procedure, in which participants indicated if a particular test stimulus matched the memorized stimulus or not. In Experiment 2 participants attempted to either reproduce the locations or they picked the color from a whole range of possibilities. Both experiments revealed effects of dynamic visual noise (DVN) on memory for colors but not for locations. The implications of the results for theories of working memory and the methodological prospects for DVN as an experimental tool are discussed.


1977 ◽  
Vol 17 (8) ◽  
pp. 903-910 ◽  
Author(s):  
Joseph J. Mezrich ◽  
Albert Rose

Sign in / Sign up

Export Citation Format

Share Document