![When it comes to neural networks learning motion, it’s all relative When it comes to neural networks learning motion, it’s all relative](https://search.ai.wiki/wp-content/uploads/2023/03/when-it-comes-to-neural-networks-learning-motion-its-all-relative.jpg)
When it comes to neural networks learning motion, it’s all relative
Seeking to explore the capabilities of neural networks for recognizing and predicting motion, a group of researchers led by Hehe Fan developed and tested a deep learning approach based on relative change in position encoded as a series of vectors, finding that their method worked better than existing frameworks for modeling motion. The group's key innovation was to encode motion separately from position.