|
|
|
|
|
by tim333
3604 days ago
|
|
It depends a bit on what you are trying to achieve but I think hooking neural type networks together to simulate human mental faculties might be a better way forward. For instance much of human thinking seems to work around visualizing things in 3d space so you can say to someone imagine a dog on a skateboard on top of a hill and you give it a push, what happens? Once you've got that kind of stuff working with spatial awareness, cause and effect and so on using neural type processing I think the language understanding would come fairly naturally. |
|