A double experiment of neural networks (one logical, one emotional)?

Question

Seeing that, as far as we know, one half of your brain is logical and the other half of your brain is emotional and that the needs of the emotional side are fed by the logical side to fulfill these desires; was there any study done to connect two separate neural networks to each other (one trained to be emotional and one trained logical) to see if this would lead to an almost arbitrary kind of “brain”?

I really don't know anything about neural networks, except that they were modeled after biological synapses in the human brain, which is why I ask.

I’m not even sure that this is possible, given that even a trained neural network sometimes does not act logically (aka to do what you thought you trained it for).

Answer 1

First, most modern neural networks are not actually modeled after biological synapses. They use an artificial neuron that allows Back Propagation to work, rather than Perceptron, which is a much more accurate representation.

When you feed the output of one network to the input of another network, you really only created one large network, not two separate networks. It just happens that in this case parts of the networks will be trained independently.

, . , . , . , , , , , . "" , "" . , , "", .

.

Answer 2

, "" "". , , , . , , , , , , , , , ( ): D

- , . . , , . -betweens , . , - !

Answer 3

, . , . . , , , , . "" .

Answer 4

, , , , , . , , , , ( ). , , , , ( , , ).

This idea is supported by the proposal of Sloman and Croucher that emotion is likely to be an inevitable emerging property of a fairly advanced intellectual system. Such systems (discussed in detail in the article) will be much more complicated than straight-line neural networks. More importantly, emotions will not be something that you can localize into one part of the system.