Google’s Artificial Intelligence Built an AI That Outperforms Any Made by Humans
What is this all about?
Google’s AutoML project, designed to make AI build other AIs, has now developed a computer vision system that vastly outperforms state-of-the-art-models. The project could improve how autonomous vehicles and next-generation AI robots “see.”
Part 1 | Part 2
An AI That can Build AIs
In May 2017, researchers at Google Brain announced the creation of AutoML, an artificial intelligence (AI) that’s capable of generating its own AIs. More recently, they decided to present AutoML with its biggest challenge to date, and the AI that can build AI created a “child” that outperformed all of its human-made counterparts.
The Google researchers automated the design of machine learning models using an approach called reinforcement learning. AutoML acts as a controller neural network that develops a child AI network for a specific task. For this particular child AI, which the researchers called NASNet, the task was recognizing objects — people, cars, traffic lights, handbags, backpacks, etc. — in a video in real-time.
AutoML would evaluate NASNet’s performance and use that information to improve its child AI, repeating the process thousands of times. When tested on the ImageNet image classification and COCO object detection data sets, which the Google researchers call “two of the most respected large-scale academic data sets in computer vision,” NASNet outperformed all other computer vision systems.
According to the researchers, NASNet was 82.7% accurate at predicting images on ImageNet’s validation set. This is 1.2% better than any previously published results, and the system is also 4% more efficient, with a 43.1% mean Average Precision (mAP). Additionally, a less computationally demanding version of NASNet outperformed the best similarly sized models for mobile platforms by 3.1 percent.
See what this means for the future in the next part.