Developing a brain-based computing system

• Main Author: Aditya Narayanamoorthy
• Other Authors: Ong Yew Soon
• Format: Final Year Project
• Language: English
• Published: 2012
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
• Online Access: http://hdl.handle.net/10356/48448
• Institution: Nanyang Technological University

Artificial intelligence-related methods have long been used to solve problems in real life. These methods include cognitive learning models, where the agent solving the task does so by learning while doing the task and adapting its behaviour accordingly. A related field is brain-based computing, where a neural model is created to better monitor the working of various regions in the brain, which could help us understand how humans complete these tasks. The following report deals with the study of a brain-based computing model called Darwin XI, and comparison to a cognitive model named TD-FALCON for the purposes of a minefield navigation task i.e. navigating from a starting point with the goal of getting to a final destination without hitting mines on the way. The Darwin XI model was very much adapted to its original task, so a lot of changes had to be made to accommodate it in the mine navigation task. These included providing similar inputs as the TD-FALCON model received, modifying the basic structure of the model and so on. It was found that the Darwin XI model did not fare well in the mine navigation task. Attempts were made to understand the causes for this, and future recommendations were given to this effect.