Title :
A neural network for attentional spotlight
Author :
Leow, Wee Kheng ; Miikkulainen, Risto
Author_Institution :
Dept. of Comput. Sci., Texas Univ., Austin, TX, USA
Abstract :
The architecture and dynamics of a neural network that generates an attentional spotlight are discussed. The network has three layers. The desired position of the spotlight is indicated by activating one of the input units. The activity of the unit represents the desired size of the spotlight. A shunting feedback network serves as the output layer and produces a spotlight of the desired shape. The spotlight has a fixed maximum size (determined by network parameters) which corresponds to the largest amount of information that a vision system can process in parallel. The spotlight generation network was simulated numerically using a forward Euler method
Keywords :
computer vision; lighting; neural nets; architecture; attentional spotlight position generation; computer vision; dynamics; forward Euler method; neural network; shunting feedback network; Biological information theory; Computational modeling; Encoding; Hardware; Humans; Neural networks; Neurons; Psychology; Space technology; Visual system;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170440
