机器人生孩子?谷歌智能已经能够独立创建新智能系统

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.

在2017年5月，Google Brain研究人员对外宣布了AutoML项目，即实现智能系统独立自创建新系统。而最近，他们决定如约将有史以来这一最大挑战的试验成果公之于众，人工智能已经能够创造自己的智能系统，也可以理解为人工智能系统可以繁衍自己的“孩子”，而由人工智能系统独立创建的智能系统要优于人类所创建的任何智能系统。

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.

谷歌的研究人员使用一种叫做强化学习的方法来实现机器学习模型设计的自动化。AutoML充当控制器神经网络，针对特定的任务开发一个子人工智能网络。研究人员称这个特殊的子智能系统为NASNet，该系统能够在实时视频中识别物体，包括人、汽车、交通灯、手袋、背包等等。

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.

AutoML会评估NASNet的性能，并利用该信息来改进它的子智能系统，并数千次的重复这个过程。在对ImageNet图像分类和COCO对象检测数据集进行测试时，谷歌研究人员将这两个数据库称为“计算机视觉中最有说服力的两大学术数据库”，NASNet的表现优于其他所有计算机视觉系统。

According to the researchers, NASNet was 82.7 percent accurate at predicting images on ImageNet’s validation set. This is 1.2 percent better than any previously published results, and the system is also 4 percent more efficient, with a 43.1 percent 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.

据研究人员称，NASNet在ImageNet的验证集上预测图像的准确度为82.7%，比之前公布的任何结果都要高出1.2%，而且该系统的效率也提高了4%，平均精度为43.1%。另外，更少计算要求的NASNet的版本比移动平台的同类模型的表现要好3.1%。