Multi-input and Multi-variable systems
Machines: Problem Solving II
Neural Circuits
Machines: Problem Solving I
Ampere-Maxwell's Law: Problem-Solving
Parallel Processing
You might also read
Articles linked to this work by shared authors, journal, and citation graph.
Updated: Mar 23, 2026

Design, Surface Treatment, Cellular Plating, and Culturing of Modular Neuronal Networks Composed of Functionally Inter-connected Circuits
Published on: April 15, 2015
Jacob Schrum1, Risto Miikkulainen2
1Department of Mathematics and Computer Science, Southwestern University, Georgetown, TX 78626, USA schrum2@southwestern.edu.
This study shows modular neuroevolution can discover effective task divisions for AI agents, outperforming human designs in complex games like Ms. Pac-Man. Machine discovery offers superior strategies for multi-task learning.
Area of Science:
Background:
Purpose of the Study:
Main Methods:
Main Results:
Conclusions: