Neural networks: A requirement for intelligent systems

Throughout the years, the computational changes have brought growth to new technologies.Such
is the case of artificial neural networks, that over the years, they have given various solutions to
the industry.

Designing and implementing intelligent systems has become a crucial factor for the
innovation and development of better products for society. Such is the case of the
implementation of artificial life as well as giving solution to interrogatives that linear systems
are not able resolve.

A neural network is a parallel system, capable of resolving paradigms that linear computing
cannot. A particular case is for considering which I will cite. During summer of 2006, an
intelligent crop protection system was required by the government. This system would protect a
crop field from season plagues. The system consisted on a flying vehicle that would inspect crop
fields by flying over them.

Now, imagine how difficult this was. Anyone that could understand such a task would say that
this project was designated to a multimillionaire enterprise capable of develop such technology.
Nevertheless, it wasn’t like that. The selected company was a small group of graduated
engineers. Regardless the lack of experience, the team was qualified. The team was divided into
4 sections in which each section was designed to develop specific sub-systems. The leader was
an electronics specialist. She developed the electronic system. Another member was a mechanics
and hydraulics specialist. He developed the drive system. The third member was a system
engineer who developed all software, and the communication system. The last member was
designed to develop all related to avionics and artificial intelligence.

Everything was going fine. When time came to put the pieces together, all fitted perfectly until
they find out the robot had no knowledge about its task. What happened? The one designated to
develop all artificial intelligent forgot to “teach the system”. The solution would be easy;
however, training a neural network required additional tools. The engineer designated to develop
the intelligent system passed over this inconvenient.

It was an outsider who suggested the best solution: Acquiring neural network software. For an
affordable price, the team bought the software, and with its help, they designed and trained the
system without a problem.

The story ended satisfactorily, but just in some parts of the design. The drive system was
working perfectly as the software and the communication device. The intelligent system was
doing its job. Nonetheless, the project was a complete failure. Why? They never taught it how to
fly.

Designing a neural network efficiently

By experience, I know it is not necessary to be a programmer nor have deep knowledge about
complex neural network algorithms in order to design a neural network. There is a wide range of
neural network software out there, and most of them have good quality. My suggestion for those
looking for the answer on neural network design is to acquire all required tools. Good software
will save you thousands of hours of programming as well as in learning complex algorithms. I
have placed a review section in which you will find which software is more convenient for you.
However, you will always find all information here to develop your own.

Neural network introduction

 Introduction
 Biological Model
 Mathematical Model
o Activation Functions
 A framework for distributed representation
 Neural Network Topologies
 Training of artificial neural networks

This site is intended to be a guide on technologies of neural networks, technologies that I believe
are an essential basis about what awaits us in the future. The site is divided into 3 sections: The
first one contains technical information about the neural networks architectures known, this
section is merely theoretical, The second section is set of topics related to neural networks as:
artificial intelligence genetic algorithms, DSP's, among others.
And the third section is the site blog where I expose personal projects related to neural networks
and artificial intelligence, where the understanding of certain theoretical dilemmas can be
understood with the aid of source code programs. The site is constantly updated with new
content where new topics are added, this topics are related to artificial intelligence technologies.

Introduction
What is an artificial neural network?

An artificial neural network is a system based on the operation of biological neural networks, in
other words, is an emulation of biological neural system. Why would be necessary the
implementation of artificial neural networks? Although computing these days is truly advanced,
there are certain tasks that a program made for a common microprocessor is unable to perform;
even so a software implementation of a neural network can be made with their advantages and
disadvantages.
Advantages:

 A neural network can perform tasks that a linear program can not.
 When an element of the neural network fails, it can continue without any problem by
their parallel nature.
 A neural network learns and does not need to be reprogrammed.
 It can be implemented in any application.
 It can be implemented without any problem.
Disadvantages:

 The neural network needs training to operate.

 The architecture of a neural network is different from the architecture of microprocessors
therefore needs to be emulated.
 Requires high processing time for large neural networks.

Another aspect of the artificial neural networks is that there are different architectures, which
consequently requires different types of algorithms, but despite to be an apparently complex
system, a neural network is relatively simple.

Artificial neural networks (ANN) are among the newest signal-processing technologies in the
engineer's toolbox. The field is highly interdisciplinary, but our approach will restrict the view to
the engineering perspective. In engineering, neural networks serve two important functions: as
pattern classifiers and as nonlinear adaptive filters. We will provide a brief overview of the
theory, learning rules, and applications of the most important neural network models. Definitions
and Style of Computation An Artificial Neural Network is an adaptive, most often nonlinear
system that learns to perform a function (an input/output map) from data. Adaptive means that
the system parameters are changed during operation, normally called the training phase . After
the training phase the Artificial Neural Network parameters are fixed and the system is deployed
to solve the problem at hand (the testing phase ). The Artificial Neural Network is built with a
systematic step-by-step procedure to optimize a performance criterion or to follow some implicit
internal constraint, which is commonly referred to as the learning rule . The input/output training
data are fundamental in neural network technology, because they convey the necessary
information to "discover" the optimal operating point. The nonlinear nature of the neural network
processing elements (PEs) provides the system with lots of flexibility to achieve practically any
desired input/output map, i.e., some Artificial Neural Networks are universal mappers . There is
a style in neural computation that is worth describing.

An input is presented to the neural network and a corresponding desired or target response set at
the output (when this is the case the training is called supervised ). An error is composed from
the difference between the desired response and the system output. This error information is fed
back to the system and adjusts the system parameters in a systematic fashion (the learning rule).
The process is repeated until the performance is acceptable. It is clear from this description that
the performance hinges heavily on the data. If one does not have data that cover a significant
portion of the operating conditions or if they are noisy, then neural network technology is
probably not the right solution. On the other hand, if there is plenty of data and the problem is
poorly understood to derive an approximate model, then neural network technology is a good
choice. This operating procedure should be contrasted with the traditional engineering design,
made of exhaustive subsystem specifications and intercommunication protocols. In artificial
neural networks, the designer chooses the network topology, the performance function, the
learning rule, and the criterion to stop the training phase, but the system automatically adjusts the
parameters. So, it is difficult to bring a priori information into the design, and when the system
does not work properly it is also hard to incrementally refine the solution. But ANN-based
solutions are extremely efficient in terms of development time and resources, and in many
difficult problems artificial neural networks provide performance that is difficult to match with
other technologies. Denker 10 years ago said that "artificial neural networks are the second best
way to implement a solution" motivated by the simplicity of their design and because of their
universality, only shadowed by the traditional design obtained by studying the physics of the
problem. At present, artificial neural networks are emerging as the technology of choice for
many applications, such as pattern recognition, prediction, system identification, and control.

The Biological Model

Artificial neural networks emerged after the introduction of simplified neurons by McCulloch
and Pitts in 1943 (McCulloch & Pitts, 1943). These neurons were presented as models of
biological neurons and as conceptual components for circuits that could perform computational
tasks. The basic model of the neuron is founded upon the functionality of a biological neuron.
"Neurons are the basic signaling units of the nervous system" and "each neuron is a discrete cell
whose several processes arise from its cell body".

The neuron has four main regions to its structure. The cell body, or soma, has two offshoots from
it, the dendrites, and the axon, which end in presynaptic terminals. The cell body is the heart of
the cell, containing the nucleus and maintaining protein synthesis. A neuron may have many
dendrites, which branch out in a treelike structure, and receive signals from other neurons. A
neuron usually only has one axon which grows out from a part of the cell body called the axon
hillock. The axon conducts electric signals generated at the axon hillock down its length. These
electric signals are called action potentials. The other end of the axon may split into several
branches, which end in a presynaptic terminal. Action potentials are the electric signals that
neurons use to convey information to the brain. All these signals are identical. Therefore, the
brain determines what type of information is being received based on the path that the signal
took. The brain analyzes the patterns of signals being sent and from that information it can
interpret the type of information being received. Myelin is the fatty tissue that surrounds and
insulates the axon. Often short axons do not need this insulation. There are uninsulated parts of
the axon. These areas are called Nodes of Ranvier. At these nodes, the signal traveling down the
axon is regenerated. This ensures that the signal traveling down the axon travels fast and remains
constant (i.e. very short propagation delay and no weakening of the signal). The synapse is the
area of contact between two neurons. The neurons do not actually physically touch. They are
separated by the synaptic cleft, and electric signals are sent through chemical 13 interaction. The
neuron sending the signal is called the presynaptic cell and the neuron receiving the signal is
called the postsynaptic cell. The signals are generated by the membrane potential, which is based
on the differences in concentration of sodium and potassium ions inside and outside the cell
membrane. Neurons can be classified by their number of processes (or appendages), or by their
function. If they are classified by the number of processes, they fall into three categories.
Unipolar neurons have a single process (dendrites and axon are located on the same stem), and
are most common in invertebrates. In bipolar neurons, the dendrite and axon are the neuron's two
separate processes. Bipolar neurons have a subclass called pseudo-bipolar neurons, which are
used to send sensory information to the spinal cord. Finally, multipolar neurons are most
common in mammals. Examples of these neurons are spinal motor neurons, pyramidal cells and
Purkinje cells (in the cerebellum). If classified by function, neurons again fall into three separate
categories. The first group is sensory, or afferent, neurons, which provide information for
perception and motor coordination. The second group provides information (or instructions) to
muscles and glands and is therefore called motor neurons. The last group, interneuronal, contains
all other neurons and has two subclasses. One group called relay or projection interneurons have
long axons and connect different parts of the brain. The other group called local interneurons are
only used in local circuits.

The Mathematical Model

When creating a functional model of the biological neuron, there are three basic components of
importance. First, the synapses of the neuron are modeled as weights. The strength of the
connection between an input and a neuron is noted by the value of the weight. Negative weight
values reflect inhibitory connections, while positive values designate excitatory connections
[Haykin]. The next two components model the actual activity within the neuron cell. An adder
sums up all the inputs modified by their respective weights. This activity is referred to as linear
combination. Finally, an activation function controls the amplitude of the output of the neuron.
An acceptable range of output is usually between 0 and 1, or -1 and 1.

Mathematically, this process is described in the figure

From this model the interval activity of the neuron can be shown to be:

The output of the neuron, yk, would therefore be the outcome of some activation function on the
value of vk.

Activation functions

As mentioned previously, the activation function acts as a squashing function, such that the
output of a neuron in a neural network is between certain values (usually 0 and 1, or -1 and 1). In
general, there are three types of activation functions, denoted by Φ(.) . First, there is the
Threshold Function which takes on a value of 0 if the summed input is less than a certain
threshold value (v), and the value 1 if the summed input is greater than or equal to the threshold
value.

Secondly, there is the Piecewise-Linear function. This function again can take on the values of 0
or 1, but can also take on values between that depending on the amplification factor in a certain
region of linear operation.

Thirdly, there is the sigmoid function. This function can range between 0 and 1, but it is also
sometimes useful to use the -1 to 1 range. An example of the sigmoid function is the hyperbolic
tangent function.

The artifcial neural networks which we describe are all variations on the parallel distributed
processing (PDP) idea. The architecture of each neural network is based on very similar building
blocks which perform the processing. In this chapter we first discuss these processing units and
discuss diferent neural network topologies. Learning strategies as a basis for an adaptive system
A framework for distributed representation
An artifcial neural network consists of a pool of simple processing units which communicate by
sending signals to each other over a large number of weighted connections. A set of major
aspects of a parallel distributed model can be distinguished :

 a set of processing units ('neurons,' 'cells');

 a state of activation yk for every unit, which equivalent to the output of the unit;
 connections between the units. Generally each connection is defined by a weight wjk
which determines the effect which the signal of unit j has on unit k;
 a propagation rule, which determines the effective input sk of a unit from its external
inputs;
 an activation function Fk, which determines the new level of activation based on the
efective input sk(t) and the current activation yk(t) (i.e., the update);
 an external input (aka bias, offset) øk for each unit;
 a method for information gathering (the learning rule);
 an environment within which the system must operate, providing input signals and|if
necessary|error signals.

Processing units

Each unit performs a relatively simple job: receive input from neighbours or external sources and
use this to compute an output signal which is propagated to other units. Apart from this
processing, a second task is the adjustment of the weights. The system is inherently parallel in
the sense that many units can carry out their computations at the same time. Within neural
systems it is useful to distinguish three types of units: input units (indicated by an index i) which
receive data from outside the neural network, output units (indicated by an index o) which send
data out of the neural network, and hidden units (indicated by an index h) whose input and output
signals remain within the neural network. During operation, units can be updated either
synchronously or asynchronously. With synchronous updating, all units update their activation
simultaneously; with asynchronous updating, each unit has a (usually fixed) probability of
updating its activation at a time t, and usually only one unit will be able to do this at a time. In
some cases the latter model has some advantages.

 
Neural Network topologies
In the previous section we discussed the properties of the basic processing unit in an artificial
neural network. This section focuses on the pattern of connections between the units and the
propagation of data. As for this pattern of connections, the main distinction we can make is
between:
  Feed-forward neural networks, where the data ow from input to output units is strictly
feedforward. The data processing can extend over multiple (layers of) units, but no
feedback connections are present, that is, connections extending from outputs of units to
inputs of units in the same layer or previous layers.
 Recurrent neural networks that do contain feedback connections. Contrary to feed-
forward networks, the dynamical properties of the network are important. In some cases,
the activation values of the units undergo a relaxation process such that the neural
network will evolve to a stable state in which these activations do not change anymore. In
other applications, the change of the activation values of the output neurons are
significant, such that the dynamical behaviour constitutes the output of the neural
network (Pearlmutter, 1990).

Classical examples of feed-forward neural networks are the Perceptron and Adaline. Examples
of recurrent networks have been presented by Anderson
(Anderson, 1977), Kohonen (Kohonen, 1977), and Hopfield (Hopfield, 1982) .

Training of artifcial neural networks

A neural network has to be configured such that the application of a set of inputs produces
(either 'direct' or via a relaxation process) the desired set of outputs. Various methods to set the
strengths of the connections exist. One way is to set the weights explicitly, using a priori
knowledge. Another way is to 'train' the neural network by feeding it teaching patterns and
letting it change its weights according to some learning rule.

We can categorise the learning situations in two distinct sorts. These are:

 Supervised learning or Associative learning in which the network is trained by

providing it with input and matching output patterns. These input-output pairs can be
provided by an external teacher, or by the system which contains the neural network
(self-supervised).

 Unsupervised learning or Self-organisation in which an (output) unit is trained to

respond to clusters of pattern within the input. In this paradigm the system is supposed to
discover statistically salient features of the input population. Unlike the supervised
 learning paradigm, there is no a priori set of categories into which the patterns are to be
classified; rather the system must develop its own representation of the input stimuli.
 Reinforcement Learning This type of learning may be considered as an intermediate
form of the above two types of learning. Here the learning machine does some action on
the environment and gets a feedback response from the environment. The learning system
grades its action good (rewarding) or bad (punishable) based on the environmental
response and accordingly adjusts its parameters. Generally, parameter adjustment is
continued until an equilibrium state occurs, following which there will be no more
changes in its parameters. The selforganizing neural learning may be categorized under
this type of learning.

Modifying patterns of connectivity of Neural Networks

Both learning paradigms supervised learning and unsupervised learning result in an adjustment
of the weights of the connections between units, according to some modification rule. Virtually
all learning rules for models of this type can be considered as a variant of the Hebbian learning
rule suggested by Hebb in his classic book Organization of Behaviour (1949) (Hebb, 1949). The
basic idea is that if two units j and k are active simultaneously, their interconnection must be
strengthened. If j receives input from k, the simplest version of Hebbian learning prescribes to
modify the weight wjk with

where ϒ is a positive constant of proportionality representing the learning rate. Another common
rule uses not the actual activation of unit k but the difference between the actual and desired

activation for adjusting the weights:

in which dk is the desired activation provided by a teacher. This is often called the Widrow-Hoff
rule or the delta rule, and will be discussed in the next chapter. Many variants (often very exotic
ones) have been published the last few years.