Comparing natural and electronic nn's

john John at nine7.demon.co.uk
Sun Dec 8 11:56:01 EST 1996


First the fundamental principle of neural networks.
nn's are analog computer that can have digital inputs and outputs in the
electronic versions.
Analog computers represent things by varying levels of things instead of
combination groups of high and low outputs.

The principle aim of nn's is to prioritise the inputs for the limited 
outputs.

Animals use them to prioritise the environments suplies for the output
energy invested into limbs etc.

Banks use them to prioritise evolving business for the limited investment
output of the bank.

The easiest way to understand how a neuron works in a network, is to
compare the neuron with an individual in their social connections.

The individual will consider some individuals more important than others
to accept diolog with, and in turn they do to.

Somtimes they know the same person say a boss or a good friend.

As with people it is easier to have whole groups linked to one neuron, but
still important to have interlinking.

The way a nn learns/adapts is to alter the importance of the inputs to
the neuron or to reselect who is most important to listen to in a group.

Like lightening chooses the easiest route down a tree to the ground, so to
does inputs find their way to the output action.

The big problem in electronic nn's is finding the quikest way to choose the
conections from the cheapest ways of wired up conections to choose from.

An analogy in human groups would be to decide quickly by some method who to
choose for help with a problem from the choices you have made to to get 
aquainted with.

If you aquaint with to many you could get into a noisy time, and the 
oposite means longer times with each problem.

The method you use to select the right input to prioritise in electronic
nn's is by the use of algorythms.

The method you use in say an ofice is a guess at whats important or being
told whats important.

In an animals brain the neuron can't geuss whats important, it has to be 
told whats important.

What tells it I wonder, is geneticly told to keep randomly varying towards
a no action default or is there another network that works on the problem?

I wonder if the network of glyle cells is this selecting deciding network.

Electronic nn's will drasticaly change our lives as much as engines and
information electronics have.

It is doubely important that people understand them as besides becoming
important, the human mind is also becoming important as muscle gives way 
to machines and the human mind is neural networks.

Also the mind must adapt to the changes in relationships to the arrival of 
machines in the environment, but the variety of social and academic talent
sugests that damage to brains that requires attention, is very common.

-- 


--
This new sig, here is a bit off topic.
Pardon it, for it knows not its place in the representations of people.
Yours sincerely John *?*?*?*?Us neurons, don't KNOW that much, period?*?*?*
After all, what is existance, without socialising and alt.landfills?*?*
I want the world to get better, not on a whim, but awesome tide of tech' power
comes in, abusers and their oposition (planning purges?), grows in dangers*?*?
?*?*?*?*?*Weighing down my back is folded robot burden*?*?*?*?*?*?
Whilest the computers completly double in power every 18 months, I dream of
sucking juice from a tree, warm, comfortable, hiden and with a partner.




More information about the Neur-sci mailing list