Figure 3 - uploaded by Thomas E. Portegys
Content may be subject to copyright.
Download
View publication
-Door training

-Door training

Source publication
Figure 1 -Context maze.
Figure 3 -Door training
A MODULAR LEARNING COMPARISON OF LONG SHORT-TERM MEMORY AND MORPHOGNOSIS NEURAL NETWORKS
Preprint
Full-text available
  • Feb 2021
This study compares the modular learning performance of two artificial neural network architectures: a Long Short-Term Memory (LSTM) recurrent network, and Morphognosis, a neural network based on a hierarchy of spatial and temporal contexts. Mazes are used to measure performance, defined as the ability to utilize independently learned mazes to solv...
Cite
Download full-text

Context in source publication

Context 1
... door must be trained with every intervening context maze, meaning that each additional/fewer door raises/lowers the number of training samples by the number of intervening context mazes. Figure 3 shows that training validation results and Figure 4 shows the testing results. ...