reversing conway’s game of life jonathan goetz. the rules of the game 1 living neighbor = cell...

5
Reversing Conway’s Game of Life Jonathan Goetz 0100 0110 0110 0010

Upload: audra-turner

Post on 24-Dec-2015

215 views

Category:

Documents


1 download

TRANSCRIPT

Page 1: Reversing Conway’s Game of Life Jonathan Goetz. The Rules of the Game 1 living neighbor = cell dies 2 living neighbors = cell maintains 3 living neighbors

Reversing Conway’s Game of Life

Jonathan Goetz

0100011001100010

Page 2: Reversing Conway’s Game of Life Jonathan Goetz. The Rules of the Game 1 living neighbor = cell dies 2 living neighbors = cell maintains 3 living neighbors

The Rules of the Game

• 1 living neighbor = cell dies• 2 living neighbors = cell maintains• 3 living neighbors = cell lives• 4-8 living neighbors = cell dies

• Many states share descendants• Some states have no ancestors• Some states are their own ancestors• Information is lost

0110100000010110

In Reverse?

Page 3: Reversing Conway’s Game of Life Jonathan Goetz. The Rules of the Game 1 living neighbor = cell dies 2 living neighbors = cell maintains 3 living neighbors

Challenges

• Loss of information prevents traditional back calculation of initial state

• The problem itself maps rather easily to a 400 input and 400 output MLP pattern classification which is applied recursively.

0100011001100010

Page 4: Reversing Conway’s Game of Life Jonathan Goetz. The Rules of the Game 1 living neighbor = cell dies 2 living neighbors = cell maintains 3 living neighbors

Details

• The basic structure is a multilayered set of MLPs which rescales the result to a range of 0-1 before reapplying the same MLP in order to approximate the input layout.

• Initial attempts to create a variable depth training weighting were not successful.

0110100000010110

Page 5: Reversing Conway’s Game of Life Jonathan Goetz. The Rules of the Game 1 living neighbor = cell dies 2 living neighbors = cell maintains 3 living neighbors

Status

• Initial attempts at rewriting the training process for between 1-5 levels of difference unsuccessful.

• Instead implementing this by converting every multi-generational training data point into multiple 1 generation steps.

0100011001100010