Google researchers automated the design of machine learning models using an approach called reinforced learning. AutoML acts as a controlling neural network that develops a child artificial intelligence network for a specific task. For this particular child AI, which researchers called NASNet, the task was to recognize objects (people, cars, traffic lights, bags, backpacks, etc.) in a video in real time.

See original (not translated) news ➥

 

See translated news ➥