WELCOME TO MY BLOG

WELCOME TO MY BLOG

Artificial neural networks

hi guys my self niyaz ahmed when i recently gave a seminar on artificial intelligence i found neural networks vry much intresting so sharing with u al folks..

An artificial neural network (ANN), usually called neural network (NN), is a mathematical model or computational model that is inspired by the structure and/or functional aspects of biological neural networks. A neural network consists of an interconnected group of artificial neurons, and it processes information using a connectionist approach to computation. In most cases an ANN is anadaptive system that changes its structure based on external or internal information that flows through the network during the learning phase. Modern neural networks are non-linear statistical data modeling tools. They are usually used to model complex relationships between inputs and outputs or to find patterns in data.

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 are among the newest signal processing technologies nowadays. The field of work is very interdisciplinary, but the explanation I will give you here will be restricted to an engineering perspective.
In the world of engineering, neural networks have two main functions: Pattern classifiers and as non linear adaptive filters. As its biological predecessor, an artificial neural network is an adaptive system. By adaptive, it means that each parameter is changed during its operation and it is deployed for solving the problem in matter. This is called the training phase.
A artificial neural network is developed with a systematic step-by-step procedure which optimizes a criterion commonly known as the learning rule. The input/output training data is fundamental for these networks as it conveys the information which is necessary to discover the optimal operating point. In addition, a non linear nature make neural network processing elements a very flexible system.

Basically, an artificial neural network is a system. A system is a structure that receives an input, process the data, and provides an output. Commonly, the input consists in a data array which can be anything such as data from an image file, a WAVE sound or any kind of data that can be represented in an array. Once an input is presented to the neural network, and a corresponding desired or target response is set at the output, an error is composed from the difference of the desired response and the real system output.
The error information is fed back to the system which makes all adjustments to their parameters in a systematic fashion (commonly known as the learning rule). This process is repeated until the desired output is acceptable. It is important to notice that the performance hinges heavily on the data. Hence, this is why this data should pre-process with third party algorithms such as DSP algorithms.
In neural network design, the engineer or designer chooses the network topology, the trigger function or performance function, learning rule and the criteria for stopping the training phase. So, it is pretty difficult determining the size and parameters of the network as there is no rule or formula to do it. The best we can do for having success with our design is playing with it. The problem with this method is when the system does not work properly it is hard to refine the solution. Despite this issue, neural networks based solution is very efficient in terms of development, time and resources. By experience, I can tell that artificial neural networks provide real solutions that are difficult to match with other technologies.
Fifteen years ago, Denker said: “artificial neural networks are the second best way to implement a solution” this motivated by their simplicity, design and universality. Nowadays, neural network technologies are emerging as the technology choice for many applications, such as patter recognition, prediction, system identification and control.

The Biological Model

Artificial neural networks born after McCulloc and Pitts introduced a set of simplified neurons in 1943. These neurons were represented as models of biological networks into conceptual components for circuits that could perform computational tasks. The basic model of the artificial neuron is founded upon the functionality of the biological neuron. By definition, “Neurons are basic signaling units of the nervous system of a living being in which each neuron is a discrete cell whose several processes are from its cell body”

The biological neuron has four main regions to its structure. The cell body, or soma, has two offshoots from it. The dendrites and the axon end in pre-synaptic terminals. The cell body is the heart of the cell. It contains the nucleolus and maintains protein synthesis. A neuron has many dendrites, which look like a tree structure, receives signals from other neurons.
A single neuron usually has one axon, which expands off from a part of the cell body. This I called the axon hillock. The axon main purpose is to conduct electrical signals generated at the axon hillock down its length. These signals are called action potentials.
The other end of the axon may split into several branches, which end in a pre-synaptic terminal. The electrical signals (action potential) that the neurons use to convey the information of the brain are all identical. The brain can determine which type of information is being received based on the path of the signal.
The brain analyzes all patterns of signals sent, and from that information it interprets the type of information received. The myelin is a fatty issue that insulates the axon. The non-insulated parts of the axon area are called Nodes of Ranvier. At these nodes, the signal traveling down the axon is regenerated. This ensures that the signal travel down the axon to be fast and constant.
The synapse is the area of contact between two neurons. They do not physically touch because they are separated by a cleft. The electric signals are sent through chemical interaction. The neuron sending the signal is called pre-synaptic cell and the neuron receiving the electrical signal is called postsynaptic cell.
The electrical signals are generated by the membrane potential which is based on differences in concentration of sodium and potassium ions and outside the cell membrane.
Biological neurons can be classified by their function or by the quantity of processes they carry out. When they are classified by processes, they fall into three categories: Unipolar neurons, bipolar neurons and multipolar neurons.
Unipolar neurons have a single process. Their dendrites and axon are located on the same stem. These neurons are found in invertebrates.
Bipolar neurons have two processes. Their dendrites and axon have two separated processes too.
Multipolar neurons: These are commonly found in mammals. Some examples of these neurons are spinal motor neurons, pyramidal cells and purkinje cells.
When biological neurons are classified by function they fall into three categories. The first group is sensory neurons. These neurons provide all information for perception and motor coordination. The second group provides information to muscles, and glands. There are called motor neurons. The last group, the interneuronal, contains all other neurons and has two subclasses. One group called relay or protection interneurons. They are usually found in the brain and connect different parts of it. The other group called local interneurons are only used in local circuits.

The Mathematical Model

Once modeling an artificial functional model from the biological neuron, we must take into account three basic components. First off, the synapses of the biological neuron are modeled as weights. Let’s remember that the synapse of the biological neuron is the one which interconnects the neural network and gives the strength of the connection. For an artificial neuron, the weight is a number, and represents the synapse. A negative weight reflects an inhibitory connection, while positive values designate excitatory connections. The following components of the model represent the actual activity of the neuron cell. All inputs are summed altogether and modified by the weights. This activity is referred as a linear combination. Finally, an activation function controls the amplitude of the output. For example, an acceptable range of output is usually between 0 and 1, or it could be -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. 

particle collision...!!

According to my back of the envelope calculations, a Saturn V Rocket requires 100 gigajoules of energy to reach orbit. A Saturn V Rocket weighs about 3,350 tons, which works out to about 30 megajoules per ton. Each magnet in the Large Hadron collider holds a little less than 10 megajoules of energy and weighs about ten tons. Therefore, perhaps we could assume that the power required to launch one of these magnets into orbit would be 300 megajoules. In total, the Large Hadron Collider produces 10 gigajoules of energy. 

We know that when a rocket is travelling through space it does so with its engines shut down. It coasts and maintains its velocity because it has ‘conserved momentum'. Given the equivalence that exists between energy and mass, Einstein would refer to this ‘conserved momentum' as the ‘relativistic mass' of an object, since an increase in conserved energy translates into an increase in relative mass of an object. The faster an object is travelling, the greater becomes its mass, and ever increasing energy is required to accelerate this increasing mass. We must ask why it is that an increase in the energetic density of an object translates into acceleration and an increase in velocity, and this leads us to conclude that ‘the empty vacuum of space' does not exist, but rather than the universe must consist of a gigantic energy field and that objects are in motion in this energy field for the same reason that objects are in motion within any magnetic field. We know that the energy represented by this ‘conserved momentum' cannot be stored within an atom, for then the result would be ‘ionization' (as the energy level of the atom increases it comes apart at the seams and hurls out over-energetic electrons). Therefore it must be the case that all momentum is conserved in the magnetic field (the field energy surrounding all objects including atoms).

The Collider consists of 1,200 magnets and these magnets store 10 Gigajoules of energy, and so therefore each individual magnet must store a little under 10 megajoules of energy. It is interesting to note that in the pictures of the damage suffered by the Large Hadron Collider, there is clear evidence of upward momentum. The magnets that tore loose from their moorings moved up. 








According to the Unified Field Theory I have been proposing, all ‘momentum' must be stored within a magnetic field, because there isn't any other obvious place to store such momentum. Therefore it must be true that if an object generates a magnetic field of sufficient strength, it should begin to move within a gravitational field, since the Unified Field Theory holds that a gravitational field is actually a magnetic field ‘in disguise' The purpose of a magnetic field is to create a perfectly even distribution of energy (a smooth featureless grey) but this purpose is frustrated by atoms, which are treated as units of energy which need to be ‘sorted' by the magnetic field, but resist sorting because atoms are packets of energy that cannot be broken up. As atoms attempt to move to the area of the field where their energy level requires them to be, they are prevented from moving by debris which is also attempting to fall downward to the correct level in the field and the result is a perpetually frustrated falling motion which we interpret as ‘gravity'.

As the energy level of the magnet increases it cannot fall down, because this would result in an increase in the energetic density of the field, and therefore the only solution is for the magnet to pushed up (a magnetic field has increasing density closer to the center of the field and the lines of flux indicate a decreasing density of field energy as distance from the center of the field increases). Since the function of a magnetic field is to create a smooth and even energetic density, moving an energetically dense object down in the field represents a forbidden energy state and therefore the only possible motion is upwards towards a region of decreasing density.

It would take 300 megajoules to put one of those magnets into orbit, according to this hypothesis, but perhaps 10 megajoules would be adequate to cause the magnet to rise a few feet. If this hypothesis proves to be correct then it would turn out that the Large Hadron Collider would never be able to function in manner to fulfill its original purpose, but instead would turn out to be an experiment which verified the Unified Field Theory. If this was true we should expect the Collider to continue to malfunction and suffer damage, since it turns out that the Collider was designed to specifications based upon faulty physics, and thus served instead as an unintended experiment to test the hypothesis of the Unified Field Theory. 







The Collider is scheduled to come back on line in July of 2009, with improvements designed to dump energy out of the interconnects. It would also be interesting to include sensors designed to detect ‘upward momentum', although this is unlikely to be something that will be done at the present time, since this idea is currently outside the bounds of conventional physics, and it would require further breakage of the device before the idea of testing this hypothesis is given serious consideration.

Large Hadron Collider

The Large Hadron Collider

Our understanding of the Universe is about to change...

The Large Hadron Collider (LHC) is a gigantic scientific instrument near Geneva, where it spans the border between Switzerland and France about 100 m underground. It is a particle accelerator used by physicists to study the smallest known particles – the fundamental building blocks of all things. It will revolutionise our understanding, from the minuscule world deep within atoms to the vastness of the Universe.

Two beams of subatomic particles called 'hadrons' – either protons or lead ions – will travel in opposite directions inside the circular accelerator, gaining energy with every lap. Physicists will use the LHC to recreate the conditions just after the Big Bang, by colliding the two beams head-on at very high energy. Teams of physicists from around the world will analyse the particles created in the collisions using special detectors in a number of experiments dedicated to the LHC.

There are many theories as to what will result from these collisions, but what's for sure is that a brave new world of physics will emerge from the new accelerator, as knowledge in particle physics goes on to describe the workings of the Universe. For decades, the Standard Model of particle physics has served physicists well as a means of understanding the fundamental laws of Nature, but it does not tell the whole story. Only experimental data using the higher energies reached by the LHC can push knowledge forward, challenging those who seek confirmation of established knowledge, and those who dare to dream beyond the paradigm.

Bertrand Arthur William Russell

Bertrand Arthur William Russell a well-known scientist once gave a public lecture on astronomy. He described how the earth orbits around the sun and how the sun, in turn, orbits around the centre of a vast collection of stars called our galaxy(milky way). At the end of the lecture, a little old lady at the back of the room got up and said: “what you have told is rubbish. The world is really flat plate supported on the back of a giant tortoise .” the scientist gave a superior smile before replying, “what is tortoise standing on ?” .. she replied smiling:  you’re very clever, young man, very clever.

planet eart..intro to our home

Earth (or the Earth) is the third planet from the Sun, and the densest and fifth-largest of the eight planets in the Solar System. It is also the largest of the Solar System's four terrestrial planets. It is sometimes referred to as the World, the Blue Planet,^[20] or by its Latin name, Terra.^{[note 6]}

Earth formed 4.54 billion years ago, and life appeared on its surface within one billion years.^[21] The planet is home to millions of species, includinghumans.^[22] Earth's biosphere has significantly altered the atmosphere and other abiotic conditions on the planet, enabling the proliferation of aerobic organisms as well as the formation of the ozone layer which, together with Earth's magnetic field, blocks harmful solar radiation, permitting life on land.^[23] The physical properties of the Earth, as well as its geological history and orbit, have allowed life to persist during this period. The planet is expected to continue supporting life for at least another 500 million years.^[24][25]

Earth's outer surface is divided into several rigid segments, or tectonic plates, that migrate across the surface over periods of many millions of years. About 71% of the surface is covered by salt water oceans, with the remainder consisting of continents and islands which together have many lakes and other sources of water that contribute to the hydrosphere. Earth's poles are mostly covered with solid ice (Antarctic ice sheet) or sea ice (Arctic ice cap). The planet's interior remains active, with a thick layer of relatively solid mantle, a liquid outer core that generates a magnetic field, and a solid iron inner core.

Earth interacts with other objects in space, especially the Sun and the Moon. At present, Earth orbits the Sun once every 366.26 times it rotates about its own axis, which is equal to 365.26 solar days, or one sidereal year.^{[note 7]} The Earth's axis of rotation is tilted 23.4° away from theperpendicular of its orbital plane, producing seasonal variations on the planet's surface with a period of one tropical year (365.24 solar days).^[26]Earth's only known natural satellite, the Moon, which began orbiting it about 4.53 billion years ago, provides ocean tides, stabilizes the axial tilt, and gradually slows the planet's rotation. Between approximately 3.8 billion and 4.1 billion years ago, numerous asteroid impacts during the Late Heavy Bombardment caused significant changes to the greater surface environment.

Both the mineral resources of the planet, as well as the products of the biosphere, contribute resources that are used to support a global human population. These inhabitants are grouped into about 200 independent sovereign states, which interact through diplomacy, travel, trade, and military action. Human cultures have developed many views of the planet, including personification as a deity, a belief in a flat Earth or in the Earth as the center of the universe, and a modern perspective of the world as an integrated environment that requires stewardship.