A modularity comparison of Long Short-Term Memory and Morphognosis neural networks
This addresses the problem of modularity in neural networks for AI researchers, but it is incremental as it compares two existing architectures on a specific task.
The study compared the modularity performance of LSTM and Morphognosis neural networks on maze tasks, finding that Morphognosis significantly outperformed LSTM in testing on modular tasks involving independently learned mazes.
This study compares the modularity 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 solve mazes composed of them. A maze is a sequence of rooms connected by doors. The modular task is implemented as follows: at the beginning of the maze, an initial door choice forms a context that must be retained until the end of an intervening maze, where the same door must be chosen again to reach the goal. For testing, the door-association mazes and separately trained intervening mazes are presented together for the first time. While both neural networks perform well during training, the testing performance of Morphognosis is significantly better than LSTM on this modular task.