Neural network (with Jeff Heaton Encog) simulates computer memory

Question

I want to simulate computer memory using the jeff heaton encog neural network library. I just don’t know which approach to use.

My requirement is to have a memory place and a set of bytes for the values.

location [0000]:byte-data[0101010]
location [0001]:byte-data[0101010]

These are the values ​​that I pass to the neural network system.

I tried to avoid retraining the neural network every time the memory data changes. But perhaps this is what I need to do.

What neural network methods would you use to achieve what I'm trying to do?

Answer 1

, , - . , , . , . , . , , , " " . , , , , . , .

, , , , . , , , node, . , , ( ). , "" , ( ). , .

(back perpogation) () - . , , . , , , , .

, , . , - -.

, - : p

Answer 2

- . , Encog.

Answer 3

Not to be too non-technical, but I'm sure a series of loops coming out of a bunch of linked loops can produce memory.

Each cycle allows you to surround data, and each cycle below it can identify, retrieve, or modify memory.

Of course, I'm not sure how you get the network to include this project.