Publication Details
Title: A Network for Extracting the Locations of Point Clusters Using Selective Attention
Author: S. Ahmad and S. Omohundro
Group: ICSI Technical Reports
Date: May 1990
PDF: ftp://ftp.icsi.berkeley.edu/pub/techreports/1990/tr-90-011.pdf
Overview:
This report explores the problem of dynamically computing visual relations in connectionist systems. It concentrates on the task of learning whether three clumps of points in a 256x256 image form an equilateral triangle. We argue that feed-forward networks for solving this task would not scale well to images of this size. One reason for this is that local information does not contribute to the solution: it is necessary to compute relational information such as the distances between points. Our solution implements a mechanism for dynamically extracting the locations of the point clusters. It consists of an efficient focus of attention mechanism and a cluster detection scheme. The focus of attention mechanism allows the system to select any circular portion of the image in constant time. The cluster detector directs the focus of attention to clusters in the image. These two mechanisms are used to sequentially extract the relevant coordinates. With this new representation (locations of the points) very few training examples are required to learn the correct function. The resulting network is also very compact: the number of required weights is proportional to the number of input pixels.
Bibliographic Information:
ICSI Technical Report TR-90-011
Bibliographic Reference:
S. Ahmad and S. Omohundro. A Network for Extracting the Locations of Point Clusters Using Selective Attention. ICSI Technical Report TR-90-011, May 1990
Author: S. Ahmad and S. Omohundro
Group: ICSI Technical Reports
Date: May 1990
PDF: ftp://ftp.icsi.berkeley.edu/pub/techreports/1990/tr-90-011.pdf
Overview:
This report explores the problem of dynamically computing visual relations in connectionist systems. It concentrates on the task of learning whether three clumps of points in a 256x256 image form an equilateral triangle. We argue that feed-forward networks for solving this task would not scale well to images of this size. One reason for this is that local information does not contribute to the solution: it is necessary to compute relational information such as the distances between points. Our solution implements a mechanism for dynamically extracting the locations of the point clusters. It consists of an efficient focus of attention mechanism and a cluster detection scheme. The focus of attention mechanism allows the system to select any circular portion of the image in constant time. The cluster detector directs the focus of attention to clusters in the image. These two mechanisms are used to sequentially extract the relevant coordinates. With this new representation (locations of the points) very few training examples are required to learn the correct function. The resulting network is also very compact: the number of required weights is proportional to the number of input pixels.
Bibliographic Information:
ICSI Technical Report TR-90-011
Bibliographic Reference:
S. Ahmad and S. Omohundro. A Network for Extracting the Locations of Point Clusters Using Selective Attention. ICSI Technical Report TR-90-011, May 1990