在文献[1]中,作者提出来,从照片的历史数据([math]\displaystyle{ x\left(t\right) }[/math])识别运动物体([math]\displaystyle{ y\left(t\right) }[/math])
参考文献
- ↑ Russell Stewart, Stefano Ermon, Label-Free Supervision of Neural Networks with Physics and Domain Knowledge, arXiv:1609.05566