Neural Network Design and the Complexity of Learning

reportActive / Technical Report | Accession Number: ADA450825 | Open PDF

Abstract:

We formalize a notion of learning that characterizes the training of feed-forward networks. In the field of learning theory, it stands as a new model specialized for the type of learning problems that arise in connectionist networks. The formulation is similar to Vallants Val84 in that we ask what can be feasibly learned from examples and stored in a particular data structure.

Author(s):
Judd, J. S.
Author Organization(s):
CALIFORNIA INST OF TECH PASADENA DEPT OF COMPUTER SCIENCE
Descriptive Note:
Doctoral thesis
Pagination:
0133

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution:
Approved For Public Release
Distribution Statement:
Approved For Public Release; Distribution Is Unlimited.

RECORD

Collection: TR
Identifying Numbers
Report Number(s):
CALTECH-CS-TR-88-20
Contract/Grant Number(s):
F33615-83-C-1078, AFOSR-87-0030
Monitor Series:
AFOSR
 Subject Terms
Communities of Interest:
No COI(s) Identified
Descriptor(s):
*NEURAL NETS, *LEARNING, DATA BASES, MODELS, FIELD THEORY, COGNITION, MEMORY(PSYCHOLOGY), THESES
Field(s)/Group(s):
Psychology, Anatomy and Physiology
Report Date:
1988 Sep 01
Creation Date:
2006 Aug 09