TY - JOUR
T1 - Brain-structured Connectionist Networks that Perceive and Learn
AU - Honavar, Vasant
AU - Uhr, Leonard
N1 - Funding Information:
Vasant Honavar & Leonard Uhr, Computer Sciences Department, University of Wisconsin-Madison, 1210 W. Dayton Street, Madison, WI 53706, USA. e-mail: [email protected]. This research was partially supported by grants from the Air Force Office of Scientific Research (AFOSR-89-0178), the National Science Foundation (CCR-8720060), and the University of Wisconsin Graduate School. The authors wish to thank the anonymous reviewers of the paper for their many helpful comments and suggestions.
PY - 1989/1/1
Y1 - 1989/1/1
N2 - This paper specifies the main features of connectionist and brain-like connectionist models; argues for the need for, and usefulness of appropriate successively larger brainlike structures; and examines parallel-hierarchical Recognition Cone models of perception from this perspective, as examples of networks exploiting such structures (e.g local receptive fields, global convergence-divergence). The anatomy, physiology, behavior and development of the visual system are briefly summarized to motivate the architecture of brain-structured networks for perceptual recognition. Results are presented from simulations of carefully pre-designed Recognition Cone structures that perceive objects (e.g. houses) in digitized photographs. A framework for perceptual learning is introduced, including mechanisms for generation learning, i.e. the growth of new links and possibly, nodes, subject to brain-like topological constraints. The information processing transforms discovered through feedback-guided generation are fine-tuned by ftedback-guided reweighting of links. Some preliminary results are presented of brain-structured networks that learn to recognize simple objects (e.g. letters of the alphabet, cups, apples, bananas) through generation and reweighting of transforms. These show large improvements over networks that either lack brain-like structure or/and learn by reweighting of links alone. It is concluded that brain-like structures and generation learning can significantly increase the power of connectionist models.
AB - This paper specifies the main features of connectionist and brain-like connectionist models; argues for the need for, and usefulness of appropriate successively larger brainlike structures; and examines parallel-hierarchical Recognition Cone models of perception from this perspective, as examples of networks exploiting such structures (e.g local receptive fields, global convergence-divergence). The anatomy, physiology, behavior and development of the visual system are briefly summarized to motivate the architecture of brain-structured networks for perceptual recognition. Results are presented from simulations of carefully pre-designed Recognition Cone structures that perceive objects (e.g. houses) in digitized photographs. A framework for perceptual learning is introduced, including mechanisms for generation learning, i.e. the growth of new links and possibly, nodes, subject to brain-like topological constraints. The information processing transforms discovered through feedback-guided generation are fine-tuned by ftedback-guided reweighting of links. Some preliminary results are presented of brain-structured networks that learn to recognize simple objects (e.g. letters of the alphabet, cups, apples, bananas) through generation and reweighting of transforms. These show large improvements over networks that either lack brain-like structure or/and learn by reweighting of links alone. It is concluded that brain-like structures and generation learning can significantly increase the power of connectionist models.
UR - http://www.scopus.com/inward/record.url?scp=0000212135&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0000212135&partnerID=8YFLogxK
U2 - 10.1080/09540098908915633
DO - 10.1080/09540098908915633
M3 - Article
AN - SCOPUS:0000212135
SN - 0954-0091
VL - 1
SP - 139
EP - 159
JO - Connection Science
JF - Connection Science
IS - 2
ER -