Funding Programme or Company Name:
Govt. of Ireland Postgraduate Scholarship
Funding Body:
Irish Research Council (IRC)
Description:
Artificial Intelligence (AI) today enables machines to perform complex tasks by simulating the way human brain works. This relies on recent advances in Artificial Neural Networks, the most widely algorithm for AI that succeeded where AI failed for decades. Artificial Neural Networks today can leverage large amounts of available data to self-train themselves to perform hard tasks such as recognising objects in an image or understanding languages. Despite this recent success of Artificial Neural Networks, the process they use to perform these tasks cannot be interpreted or understood by humans. Therefore we cannot know how the system arrived at its conclusion or which steps it used to solve the task; all we know is how good the solution is. This research aims to help make the AI process based on Artificial Neural Networks understandable by humans. We also aim to incorporate two aspects the algorithm currently lacks: the ability to extract relationships such as causality between elements involved in learning to perform a task, and the ability to use background knowledge when learning, both typical of human decision making and reasoning. Decision due March 2018
Insight Contact:
Application Domain:
Research Group:
Associated Theme for Application Domain:
The Discovery Economy-Discovery Analytics
Involved Institution:
Dublin City University (DCU)
Non-Insight Contact:
Sean Quinn