CaltechTHESIS
  A Caltech Library Service

Invariance hints and the VC dimension

Citation

Fyfe, William John Andrew (1992) Invariance hints and the VC dimension. Dissertation (Ph.D.), California Institute of Technology. doi:10.7907/ft2z-te28. https://resolver.caltech.edu/CaltechETD:etd-07202007-075240

Abstract

We are interested in having a neural network learn an unknown function f. If the function satisfies an invariant of some sort, such as f is an odd function, then we want to be able to take advantage of this information and not have the network deduce the invariant based on an example of f.

The invariant might be defined in terms of an explicit transformation of the input space under which f is constant. In this case it is possible to build a network that necessarily satisfies the invariant.

In general, we define the invariant in terms of a partition of the input space such that if x, x' are in the same partition element then f(x) = f(x'). An example of the invariant would be a a pair (x, x') taken from a single partition element. We can combine examples of the invariant with examples of the function in the learning process. The goal is to substitute examples of the invariant for examples of the function; the extent to which we can actually do this depends on the appropriate VC dimensions. Simulations verify, at least in simple cases, that examples of the invariant do aid the learning process.

Item Type:Thesis (Dissertation (Ph.D.))
Degree Grantor:California Institute of Technology
Division:Engineering and Applied Science
Major Option:Computer Science
Thesis Availability:Public (worldwide access)
Research Advisor(s):
  • Abu-Mostafa, Yaser S.
Thesis Committee:
  • Abu-Mostafa, Yaser S. (chair)
  • Barr, Alan H.
  • Mead, Carver
  • Posner, Edward C.
  • Wilson, Richard M.
Defense Date:26 May 1992
Record Number:CaltechETD:etd-07202007-075240
Persistent URL:https://resolver.caltech.edu/CaltechETD:etd-07202007-075240
DOI:10.7907/ft2z-te28
Default Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:2950
Collection:CaltechTHESIS
Deposited By: Imported from ETD-db
Deposited On:20 Jul 2007
Last Modified:16 Apr 2021 22:59

Thesis Files

[img]
Preview
PDF (Fyfe_wja_1992.pdf) - Final Version
See Usage Policy.

3MB

Repository Staff Only: item control page