Neural Networks for Mobile Robot Navigation [closed]

As it currently stands, this question is not a good fit for our Q&A format. We expect answers to be supported by facts, references, or expertise, but this question will likely solicit debate, arguments, polling, or extended discussion. If you feel that this question can be improved and possibly reopened, v开发者_高级运维isit the help center for guidance. Closed 10 years ago.

When designing mobile robot navigation using Artificial Neural Networks - there is a preference to use Back Propagation Methods instead of Feed Forward Methods, Why ?

---

Like Eric said, back-prop isn't an alternative to a feed forward networks -- its an addition. With just a feed forward network, your left with the task of figuring out all of the weights yourself, which very rarely makes sense.

Now, back-prop isn't a necessary addition, as there numerous other learning methods ranging from reinforcement learning to evolutionary methods like genetic programming. But you pretty much have to add some learning algorithm to your network to achieve any sort of decent task performance.