One and Zero an Introduction to Artificial Intelligence

Introductioninput information to the output.
Human beings and machines may have much in3. One output layer to give the answers, in this
common. Humans invent new machines all thecase yes/no if the music notes correspond to a
time and they say that the first machine evercertain song.
invented was the wheel.How does the ANN learn?
From far dark ages in history to nowadaysThe ANN learns by iterations or repetitions, and
computers age and at the core of every machinethis iterations are called epochs.
there is One and Zero.Known as the binarySo for each learning epoch in the ANN there is:
system, in fact, when you see the letter "A" in
your computer there are Ones and Zeroes behind1. Feed input data
it. When you use the most complex software or2. Propagate signal through layers
surf to your favourite web site, there are Ones3. Give an output
and Zeroes there too. Spiritual people say thatWell then, if we don't tell the net when to stop
the Universe is made of nothing (zero) andthe loop can go on forever. This flow needs to be
something (one), that the Universe is mademore elaborated by setting stopping conditions
mostly of emptiness.somewhere, sometime when it is for sure that
The film A.I. has created a myth in people's mindthe net has learned.
perceiving artificial intelligence as some kind ofLike in the biological model the neurons transmit
"magic" of the technology. Also, in the old sci-fithe electrical impulses through layers of neurons in
films we always see machines, those giganticthe brain till there is a desired output.
computers who develop independent free will toThe most known ANN model is called multilayer
take control over humans. Not so nice picture,backpropagation or multilayer perceptron, and a
huh?perceptron is simply a neuron that learns.
In this paper I will try to demystify the idea ofLet's expand the learning model a little bit more
artificial intelligence by giving simple explanationsby creating a stopping condition called the
and with no mathematics if possible, putting inminimum desired error (the ANN learns from its
your hands the simple truth: all there is behind iserrors just like us! Well, ahem! sometimes..),so:
One and Zero.
Back in 1943 McCulloch and Pitts developed1. Feed input data.
models of artificial neural networks (from now on2. Propagate signal through layers from the output
ANN) based on their understanding of neurology,last layer backwards to the first hidden layer. This
those discoveries found out how neurons learn inis backpropagation.
the human brain: by transmitting electric impulses3. Calculate current error.
through the synapses (connections) between4. Ask: Is current error smaller than the minimum
neurons.desired error? Then give output and EXIT.
We could say that neurons in our brain are united5. If current error is bigger: Go back to 1.
through a gigantic number of connections theThis model is yet a very simple model as one
makes the whole act like an enormous almostcould ask: what if the current error is never
infinite network.smaller than the minimum desired error? Then we
Well, this idea was transported to softwarecan create a second stopping condition, the
research to create an algorithm, or method, thatmaximum number of iterations (epochs) allowed.
can learn like the brain does: through connectionsIn step two (backpropagation) some necessary
and signal propagation through neurons.mathematics calculations are done to find out the
Our brain needs the input data, like reading,current error.
smelling, or hearing music, then the brain filters allThis calculations are based upon the connections
through electrical impulses and waves.between layers. I am not going to deep in the
When one listens to only a few tunes he/she canformulas details I'm just going to give the idea
recognize the melody and tell the songs namebehind it:
before the end of the play.My Actual Layer Data=My Previous Layer's
Here the input are the music notes and theCalculations.
output the song's name just recognized. Easy..And the word Previous is very important here
In the same manner we can design an ANN:because it is the way that layers are connected
to each other.
1. InputConclusion.. and what's really inside a neuron?
2. ProcessingSo far we've talked about neurons, networks,
3. Outputlayers, input and output data, backpropagation and
But a single note will not be enough to recognize aepochs.
whole melody and so the ANN needs more inputAll these words are the usual terminology in all
data to learn before being able to give a validANN papers but this paper is different and I want
output.to talk about what is inside a neuron.
Why does the ANN need layers?Inside a neuron there is One or Zero and the
The web connections in an ANN are organized inoutput solution once the network has learned is
layers, and a layer contains from one to manygiven as One (true) or Zero (false). Of course
neurons, so, for the music problem the layer'sthere are ANNs that work with real numbers like
distribution is:1.5672 but in most cases the input data is scaled
close to Zero or One values to make sure that
1. One Input layer containing information for thethe best performances are given.
ANN to learn, let's say the music notes whereAfter these very simple explanations Artificial
each note is a neuron.Intelligence is in your hands now and you can walk
2. One to several hidden layers that will connectyour way on.