Google supercomputer creates AI child known as NASNet

Tech giant, Google have created an AI child known as NASNet who recognizes objects, such as people, cars, handbags and traffic lights, in photos and videos. This AI child is controlled by a neural network called AutoML made by Google Brain which teaches the child to do specific tasks.

The machine is created through reinforcement learning approach. This approach trains the child for a particular task. The feedback is then used to inform the controller how to improve its proposals for the next round. The process is repeated thousands of times.

According to a blog post by Google, NASNet achieves a prediction accuracy of 82.7 percent on the validation set, surpassing all previous Inception models. Additionally, he performs 1.2 percent better than all previous published results.

The system is an open source and they suspect that the image features learned by NASNet on ImageNet and COCO may be reused for many computer vision applications.

Researchers hope that the developers will be able to create multitudes of computer vision problems they have not yet imagined.