InTech-Introduction To The Artificial Neural Networks PDF
InTech-Introduction To The Artificial Neural Networks PDF
InTech-Introduction To The Artificial Neural Networks PDF
(k) x
(k)
m
=0
+ b_ (1)
Where:
x
tbrcsbolJ
u i w
x
< tbrcsbolJ
(2)
When this type of transfer function is used in artificial neuron we call this artificial neuron
perceptron. Perceptron is used for solving classification problems and as such it can be most
commonly found in the last layer of artificial neural networks. In case of linear transfer
function artificial neuron is doing simple linear transformation over the sum of weighted
inputs and bias. Such an artificial neuron is in contrast to perceptron most commonly used
in the input layer of artificial neural networks. When we use non-linear function the sigmoid
function is the most commonly used. Sigmoid function has easily calculated derivate, which
can be important when calculating weight updates in the artificial neural network.
3. Artificial Neural Networks
When combining two or more artificial neurons we are getting an artificial neural network.
If single artificial neuron has almost no usefulness in solving real-life problems the artificial
neural networks have it. In fact artificial neural networks are capable of solving complex
real-life problems by processing information in their basic building blocks (artificial
neurons) in a non-linear, distributed, parallel and local way.
The way that individual artificial neurons are interconnected is called topology, architecture
or graph of an artificial neural network. The fact that interconnection can be done in
numerous ways results in numerous possible topologies that are divided into two basic
classes. Fig. 4. shows these two topologies; the left side of the figure represent simple feed-
forward topology (acyclic graph) where information flows from inputs to outputs in only
one direction and the right side of the figure represent simple recurrent topology (semi-
cyclic graph) where some of the information flows not only in one direction from input to
output but also in opposite direction. While observing Fig. 4. we need to mention that for
easier handling and mathematical describing of an artificial neural network we group
individual neurons in layers. On Fig. 4. we can see input, hidden and output layer.
Fig. 4. Feed-forward (FNN) and recurrent (RNN) topology of an artificial neural network.
www.intechopen.com
Introduction to the Artificial Neural Networks 7
When we choose and build topology of our artificial neural network we only finished half of
the task before we can use this artificial neural network for solving given problem. Just as
biological neural networks need to learn their proper responses to the given inputs from the
environment the artificial neural networks need to do the same. So the next step is to learn
proper response of an artificial neural network and this can be achieved through learning
(supervised, un-supervised or reinforcement learning). No matter which method we use, the
task of learning is to set the values of weight and biases on basis of learning data to
minimize the chosen cost function.
3.1 Feed-forward Artificial Neural Networks
Artificial neural network with feed-forward topology is called Feed-Forward artificial neural
network and as such has only one condition: information must flow from input to output in
only one direction with no back-loops. There are no limitations on number of layers, type of
transfer function used in individual artificial neuron or number of connections between
individual artificial neurons. The simplest feed-forward artificial neural network is a single
perceptron that is only capable of learning linear separable problems. Simple multi-layer
feed-forward artificial neural network for purpose of analytical description (sets of
equations (3), (4) and (5)) is shown on Fig. 5.
n
1
= F
1
(w
1
x
1
+b
1
)
n
2
= F
2
(w
2
x
2
+b
2
)
n
3
= F
2
(w
2
x
2
+b
2
)
n
4
= F
3
(w
3
x
3
+b
3
)
(3)
m
1
= F
4
(q
1
n
1
+ q
2
n
2
+b
4
)
m
2
= F
5
(q
3
n
3
+q
4
n
4
+b
5
)
y = F
6
(r
1
m
1
+r
2
m
2
+ b
6
)
(4)
y = F
6
_
r
1
(F
4
|q
1
F
1
|w
1
x
1
+b
1
] +q
2
F
2
|w
2
x
2
+b
2
]] +b
4
) +
+r
2
(F
5
|q
3
F
2
|w
2
x
2
+ b
2
] +q
4
F
3
|w
3
x
3
+b
3
] +b
5
]) +b
6
_ (5)
Fig. 5. Feed-forward artificial neural network.
www.intechopen.com
Artificial Neural Networks - Methodological Advances and Biomedical Applications 8
As seen on Fig. 5 and corresponding analytical description with sets of equations (3), (4) and
(5) the simple feed-forward artificial neural network can led to relatively long mathematical
descriptions where artificial neural networks parameters optimization problem solving by
hand is impractical. Although analytical description can be used on any complex artificial
neural network in practise we use computers and specialised software that can help us
build, mathematically describe and optimise any type of artificial neural network.
3.2 Recurrent Artificial Neural Networks
Artificial neural network with the recurrent topology is called Recurrent artificial neural
network. It is similar to feed-forward neural network with no limitations regarding back-
loops. In these cases information is no longer transmitted only in one direction but it is also
transmitted backwards. This creates an internal state of the network which allows it to
exhibit dynamic temporal behaviour. Recurrent artificial neural networks can use their
internal memory to process any sequence of inputs. Fig. 6. shows small Fully Recurrent
artificial neural network and complexity of its artificial neuron interconnections.
The most basic topology of recurrent artificial neural network is fully recurrent artificial
network where every basic building block (artificial neuron) is directly connected to every
other basic building block in all direction. Other recurrent artificial neural networks such as
Hopfield, Elman, Jordan, bi-directional and other networks are just special cases of recurrent
artificial neural networks.
Fig. 6. Fully recurrent artificial neural network.
3.3 Hopfield Artificial Neural Network
A Hopfield artificial neural network is a type of recurrent artificial neural network that is
used to store one or more stable target vectors. These stable vectors can be viewed as
memories that the network recalls when provided with similar vectors that act as a cue to
the network memory. These binary units only take two different values for their states that
are determined by whether or not the units' input exceeds their threshold. Binary units can
take either values of 1 or -1, or values of 1 or 0. Consequently there are two possible
definitions for binary unit activation o
= _
-1 i w
]
s
]
> 0
]
,
1 otbcrwisc.
(6)
o
= _
u i w
]
s
]
> 0
]
,
1 otbcrwisc.
(7)
Where:
w
]
is the strength of the connection weight from unit j to unit i,
s
]
is the state of unit j,
0