This page describes a series of experiments performed in the PhD thesis Learning to See Analogies: A Connectionist Exploration, by Doug Blank and available here.
This work was originally done in 1997. The experiments have been re-done and documented here using the pyrobot.conx Python library for neural networks.
The following experiments require a recent Pyrobot version 5.0.2 or above, and the files in Visual-analogies.zip.
For more information on the Python conx neural network simulator, please see:
To get started:
- Unzip the files into a directory, say visual-analogies
- You may need to set your PYTHONPATH environment variable to include the pyrobot directory
- run python -i visual-analogies.py
You can interrupt the processing (control+c) and interactively explore the processing:
>>> n.interactive = 1 >>> n.propagate(input=all(letters[i]), context=body(letters[i]), figure=body(letters[i]), ground=brim(letters[i]), )
More soon... see the file visual-analogies.py for more details.