Variable Binding
- The thing that has been on this to do list longest is
variable binding.
- The classic problem is the green square and the red
circle.
- All 4 base CAs are active, but how can you tell the colour of
the circle?
- Somehow they have to be bound together.
- Variable binding also gives us rules, which makes the
whole system largely Turing complete.
- Sougne has solved it using pattern oscillations, but
I think this has some real problems.
- I'd like to use binding areas of medium term memory.
- The binding node can bind red and circle together.
- It can then support the long term formation of a red-circle
CA (outside the binding area), or
- spontaneous activation can wipe it out.
- This would be a different memory system than the
short and long-term memory system in semantic memory.
- The simulations I'm working on have the same basic architecture
with some different constants.
- The idea is that the binding area both learns faster and
forgets faster.
