Investigating the possibilities for bi-directional knowledge transfer between biological and artificial intelligence.
AI has made rapid progress in recent years, overtaking human performance on complex tasks. However, there remain many areas where AI cannot compete with even simple biological organisms. Such areas include understanding object permanence and intuitive physics, one-shot learning, intelligent exploration and generalising to unexpected situations. This project explores these areas looking towards understanding and then closing the gap between biological and artificial intelligence.
Animal-AI Example Task - Transparent Cylinder:
Such tasks involve simple common-sense reasoning and are easy enough that a child should be able to solve them. Many have been passed by animals (including shrimp!). However, these tasks are still challenging for AI, and will need to be solved to create more general forms of artificial intelligence.
A list of tasks can be found on this link: http://animalai.org/AAI/testbed.
Animal videos and cylinder experiment discussion: https://www.pnas.org/doi/10.1073/pnas.1323533111.
Contact email@example.com to get more information about the project or for general inquiries.