In Brief Elon Musk co-founded artificial intelligence non-profit OpenAI just announced it has created an AI system that can learn to complete a task in reality after watching just one demonstration of that task in a simulated environment.
The research company co-founded and chaired by Elon Musk used two separate neural networks to develop its one-shot imitation learning system. Even more remarkably, the system was able to complete the task even if the starting parameters didn’t quite match up. The blocks didn’t need to be in the exact same location as the demonstration for the system to know how to stack them. If a blue block went on top of a white block in the demonstration, the system replicated that task, even if the starting locations of the blocks wasn’t identical.
Essentially, the platform gives AI the ability to replicate how humans use computers, which allows developers to train their systems to complete any computer-based tasks humans can do.
They’ve created AI systems that can learn on their own and even ones that can teach each other.