Artificial Neural Networks (Download Seminar Report)
Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Computer Science Clay
Active In SP

Posts: 712
Joined: Jan 2009
30-07-2009, 05:22 PM

Most people when asked if they think computers could ever become sentient quickly respond no and refer to the fact that computers are unable to learn. However, Neural Networks seems to do just that.

Neural Networks encompass a diverse set of computational models, which share a set of simple underlying characteristics. Inspired by the computational style of biological systems, a Neural Network can be viewed as an assembly of simple, interconnected processing units (neurons) acting in parallel, which communicate to each other using unidirectional connections.

Neural networks are distinguished from other computer and mathematical techniques by their design motivation. They are processing devices, that can be algorithms or actual hardware that are modeled after the functioning of human brain. Most Neural Networks have some sort of training rule whereby the weights of connections are adjusted on the basis of presented patterns. In other words, Neural Networks learn from examples, just like children learn to recognize dogs from examples of dogs and exhibit some structural capability for generalization.

The most significant aspects of Neural Networks are that they allow the computer to learn and they have the potential for parallelism. This means that they allow the computer to solve multiple problems at a time.

Neural Networks can perform any variety of tasks just as any regular computer. They are of greatest use in computing problems where the input does not follow clean strict rules but instead has an overall pattern. Neural Networks have applications in diverse areas like interpretation, prediction, diagnosis, planning, monitoring, debugging, repair, instruction, control, categorization and pattern recognition. Thus Neural Networks is an exponentially growing area of real- time applications of the new era.

http://seminar and presentationproject and
Use Search at wisely To Get Information About Project Topic and Seminar ideas with report/source code along pdf and ppt presenaion
Active In SP

Posts: 1,124
Joined: Jun 2010
16-10-2010, 09:50 AM

.doc   Artificial Neural Networks.doc (Size: 49 KB / Downloads: 292)

Artificial Neural Networks

During the infancy of the development of Neural Networks technology, one thing that excited people’s interest was its analogy to biological systems. Even though not all has been understood about the learning processes of human neural systems, Artificial Neural Networks (ANN) have, without a doubt, provide the solution to problems in different application areas [1]. The brain is a highly complex, nonlinear and parallel information processing system. It consists of about one hundred billion neural cells, each connected to about 10,000 neighboring neurons and receiving signals from there. The brain routinely accomplishes perceptual recognition tasks (e.g., recognizing a familiar face in a scene) in about 100-200 msec. The neuron, the basic information processing element (PE) in the central nervous system plays a very important and diverse role in human sensory processing, control and cognition. The brain is able to do complex tasks by its ability to learn from experience. An Artificial Neural network is designed to model the working of human brain.
The ANN is usually implemented using electronic components (digital & analog) and/or simulated on a digital computer. It employs massive interconnection of simple computing cells called “neurons” or “processing elements (PE)” It resembles the brain in two ways:

• Knowledge is acquired by the network through learning process,
• Inter neuron connection strength (synaptic weights) are responsible for storing the knowledge.
The way the synaptic weights change is what makes the design of ANNs. Such an approach is close to linear adaptive filter theory, which is well established and is used in many diverse fields such as communication, control, sonar, radar, and biomedical engineering.
seminar class
Active In SP

Posts: 5,361
Joined: Feb 2011
18-04-2011, 11:13 AM

Amit Kumar

.docx   ANN.docx (Size: 232.62 KB / Downloads: 253)
Artificial Neural networks are composed of simple elements operating in parallel. These elements are inspired by biological nervous systems. As in nature, the network function is determined largely by the connections between elements. We can train a neural network to perform a particular function by adjusting the values of the connections (weights) between elements. Commonly neural networks are adjusted, or trained, so that a particular input leads to a specific target output. Such a situation is shown below. There, the network is adjusted, based on a comparison of the output and the target, until the network output matches the target. Typically many such input/target pairs are used, in this supervised learning, to train a network.
Batch training of a network proceeds by making weight and bias changes based on an entire set (batch) of input vectors. Incremental training changes the weights and biases of a network as needed after presentation of each individual input vector. Incremental training is sometimes referred to as “on line” or “adaptive” training.
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 an adaptive 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.
A literature review is part of a research project and implimentation where a researcher researches on similar work to his or hers. This very important part of the research helps the researcher to find out how other researchers have tackled the problem he/she is attempting to solve. It gives insight on how to go about solving the problem at hand and provides information on available technologies and tools for solving the problem.
Perhaps the greatest advantage of ANNs is their ability to be used as an arbitrary function approximation mechanism that 'learns' from observed data. However, using them is not so straightforward and a relatively good understanding of the underlying theory is essential.
• Choice of model: This will depend on the data representation and the application. Overly complex models tend to lead to problems with learning.
• Learning algorithm: There are numerous trade-offs between learning algorithms. Almost any algorithm will work well with the correct hyperparameters for training on a particular fixed data set. However selecting and tuning an algorithm for training on unseen data requires a significant amount of experimentation.
• Robustness: If the model, cost function and learning algorithm are selected appropriately the resulting ANN can be extremely robust.
With the correct implementation, ANNs can be used naturally in online learning and large data set applications. Their simple implementation and the existence of mostly local dependencies exhibited in the structure allows for fast, parallel implementations in hardware.
The original inspiration for the term Artificial Neural Network came from examination of central nervous systems and their neurons, axons, dendrites, and synapses, which constitute the processing elements of biological neural networks investigated by neuroscience. In an artificial neural network, simple artificial nodes, variously called "neurons", "neurodes", "processing elements" (PEs) or "units", are connected together to form a network of nodes mimicking the biological neural networks — hence the term "artificial neural network".
Because neuroscience is still full of unanswered questions, and since there are many levels of abstraction and therefore many ways to take inspiration from the brain, there is no single formal definition of what an artificial neural network is. Generally, it involves a network of simple processing elements that exhibit complex global behavior determined by connections between processing elements and element parameters. While an artificial neural network does not have to be adaptive per se, its practical use comes with algorithms designed to alter the strength (weights) of the connections in the network to produce a desired signal flow.
These networks are also similar to the biological neural networks in the sense that functions are performed collectively and in parallel by the units, rather than there being a clear delineation of subtasks to which various units are assigned . Currently, the term Artificial Neural Network (ANN) tends to refer mostly to neural network models employed in statistics, cognitive psychology and artificial intelligence. Neural network models designed with emulation of the central nervous system (CNS) in mind are a subject of theoretical neuroscience and computational neuroscience.
In modern software implementations of artificial neural networks, the approach inspired by biology has been largely abandoned for a more practical approach based on statistics
and signal processing. In some of these systems, neural networks or parts of neural networks (such as artificial neurons) are used as components in larger systems that combine both adaptive and non-adaptive elements. While the more general approach of such adaptive systems is more suitable for real-world problem solving, it has far less to do with the traditional artificial intelligence connectionist models. What they do have in common, however, is the principle of non-linear, distributed, parallel and local processing and adaptation.
smart paper boy
Active In SP

Posts: 2,053
Joined: Jun 2011
20-06-2011, 04:33 PM

Submitted By :-
Vikas Sharma

.ppt   Seminarjjjj.ppt (Size: 579 KB / Downloads: 188)
Introduction to Artificial Neural Networks
Neural networks : Introduction

Neural network: information processing paradigm inspired by biological nervous systems, such as our brain
Structure: large number of highly interconnected processing elements (neurons) working together
Like people, they learn from experience (by example)
Neural networks : Introduction
Neural networks are configured for a specific application, such as pattern recognition or data classification, through a learning process
In a biological system, learning involves adjustments to the synaptic connections between neurons
 same for artificial neural networks (ANNs)
A new sort of computer
What are (everyday) computer systems good at... and not so good at?
Where can neural network systems help
when we can't formulate an algorithmic solution.
when we can get lots of examples of the behavior we require.
‘learning from experience’
when we need to pick out the structure from existing data.
Inspiration from Neurobiology
A neuron: many-inputs / one-output unit
output can be excited or not excited
incoming signals from other neurons determine if the neuron shall excite ("fire")
Synapse concept
The synapse resistance to the incoming signal can be changed during a "learning" process [1949]
Mathematical representation
The neuron calculates a weighted sum of inputs and compares it to a threshold. If the sum is higher than the threshold, the output is set to 1, otherwise to -1.
A simple perceptron
It’s a single-unit network
Change the weight by an amount proportional to the difference between the desired output and the actual output.
Δ Wi = η * (D-Y).Ii
Example: A simple single unit adaptive network
The network has 2 inputs, and one output. All are binary. The output is
1 if W0I0 + W1I1 > 0 
0 if W0I0 + W1I1 ≤ 0 
We want it to learn simple OR: output a 1 if either I0 or I1 is 1.
Artificial Neural Networks
Adaptive interaction between individual neurons
Power: collective behavior of interconnected neurons
Evolving networks
Continuous process of:
Evaluate output
Adapt weights
Take new inputs
ANN evolving causes stable state of the weights, but neurons continue working: network has ‘learned’ dealing with the problem
From experience: examples / training data
Strength of connection between the neurons is stored as a weight-value for the specific connection
Learning the solution to a problem = changing the connection weights
Learning performance
Learning Paradigms:
Competitive Learning
Reinforcement learning
Unsupervised learning
No help from the outside
No training data, no information available on the desired output
Learning by doing
Example : -
Competitive learning: example
In this type, it is generally Winner takes all concept.
only update weights of winning neuron
Back propagation
Desired output of the training examples
Error = difference between actual & desired output
Change weight relative to error size
Calculate output layer error , then propagate back to previous layer
Improved performance, very common!
Where are NN used?
Recognizing and matching complicated, vague, or incomplete patterns
Data is unreliable
Problems with noisy data
Data association
Data conceptualization
Prediction: learning from past experience
pick the best stocks in the market
predict weather
identify people with cancer risk
Image processing
Predict bankruptcy for credit card companies
Risk assessment
Pattern recognition: SNOOPE (bomb detector in U.S. airports)
Character recognition
Handwriting: processing checks
Data association
Not only identify the characters that were scanned but identify when the scanner is not working properly
Data Conceptualization
infer grouping relationships e.g. extract from a database the names of those most likely to buy a particular product.
Data Filtering
e.g. take the noise out of a telephone signal, signal smoothing
Unknown environments
Sensor data is noisy
Fairly new approach to planning

Strengths of a Neural Network
Power: Model complex functions, nonlinearity built into the network
Ease of use:
Learn by example
Very little user domain-specific expertise needed
Intuitively appealing: based on model of biology, will it lead to genuinely intelligent computers/robots?
Neural networks cannot do anything that cannot be done using traditional computing techniques, BUT they can do some things which would otherwise be very difficult.
General Advantages

Adapt to unknown situations
Robustness: fault tolerance due to network redundancy
Autonomous learning and generalization
Not exact
Large complexity of the network structure
Future of Neural Networks
Most of the reported applications are still in research stage
No formal proofs, but they seem to have useful applications that work
seminar addict
Super Moderator

Posts: 6,592
Joined: Jul 2011
06-02-2012, 11:52 AM

to get information about the topic Artificial Intelligence Neural Networks full report ,ppt and related topic refer the link bellow and presentation-report and presentation-report and presentation-report?page=3 and presentation-ppt
seminar ideas
Super Moderator

Posts: 10,003
Joined: Apr 2012
09-05-2012, 01:51 PM

Artificial Neural Networks

.pdf   ELECTRONIC_NOSE.pdf (Size: 289.11 KB / Downloads: 18)

The electronics field is developing at a fast rate. Each
day the industry is coming with new technology and
products. The electronic components play a major role in
all fields of life. The scientists had started to mimic the
biological world. The development of artificial neural
network (ANN), in which the nervous system is
electronically implemented is one among them.

To attempt to mimic the human apparatus,
researchers have identified distinct steps that characterize
the way humans smell. It all begins with sniffing, which
moves air samples that contain molecules of odors past
curved bony structures called turbinate. The turbinate
create turbulent airflow patterns that carry the mixture of
volatile compounds to that thin mucus coating of the
nose’s olfactory epithelium, where ends if the nerve cells
that sense odorants.

Enter the gas sensors of the electronic nose. This
speedy, reliable new technology undertakes what till now
has been impossible – continuous real monitoring of odor
at specific sites in the field over hours, days, weeks or even
An electronic device can also circumvent many other
problems associated with the use of human panels.
Individual variability, adaptation (becoming less sensitive
during prolonged exposure), fatigue, infections, mental
state, subjectivity, and exposure to hazardous compounds
all come to mind. In effect, the electronic nose can create
odor exposure profiles beyond the capabilities of the
human panel or GC/MS measurement techniques.

Sensing an odorant
In a typical electronic nose, an air sample is pulled
by a vacuum pump through a tube into a small chamber
housing the electronic sensor array. The tube may be
made of plastic or a stainless steel. Next, the sample–
handling unit exposes the sensors to the odorant,
producing a transient response as the VOCs interact with
the surface and bulk of the sensor’s active material.
(Earlier, each sensors has been driven to a known state by
having clean, dry air or some other reference gas passed
over its active elements.) A steady state condition is
reached in a few seconds to a few minutes, depending on
the sensor type.
seminar ideas
Super Moderator

Posts: 10,003
Joined: Apr 2012
21-05-2012, 12:05 PM

Artificial Neural Networks

.pptx   Neural networks .pptx (Size: 259.19 KB / Downloads: 26)


All learning methods used for adaptive neural networks can be classified into two major categories:
Supervised learning which incorporates an external teacher, so that each output unit is told what its desired response to input signals ought to be.
Unsupervised learning uses no external teacher and is based upon only local information. It is also referred to as self-organization, in the sense that it self-organizes data presented to the network and detects their emergent collective properties.


Neural networks are not only different in their learning processes but also different in their structures or topology. Haykin has divided the network architectures into the following three classes:
Feed-forward network.
Feedback networks.
Network layers. 


Feed-forward ANNs allow signals to travel one way only; from input to output. There is no feedback.i.e. the output of any layer does not affect that same layer.
Feed-forward ANNs tend to be straight forward networks that associate inputs with outputs. They are extensively used in pattern recognition. This type of organization is also referred to as bottom-up or top-down.
Single layer perceptrons
Multi-layer perceptrons


The single-layer perceptrons was among the first and simplest learning machines that are trainable.
whose first-layer units have fixed function with fixed connection weights from the inputs, and
whose connection weights linking this first layer to the second layer of outputs are learnable.


seminar flower
Super Moderator

Posts: 10,120
Joined: Apr 2012
19-06-2012, 11:59 AM

Artificial Neural Networks


The present work encompasses a study of image recognition and corresponding information retrieval by means of a feed forward three layer neural system in defence sector. Where the system intelligence in recognizing the patterns is checked and fault tolerance analysis of the same is done. The image to be fed to the neural net after preprocessing. To support our project and implimentation application, an appropriate neural net architecture is selected for design. Selection of proper activation function plays a very major role in the design of architecture. Applying an appropriate learning rule, the designed neural net is trained to learn the patterns.


An Artificial Neural Network (ANN) also called Neural Network is an information-processing paradigm that is inspired by the way biological nervous systems, such as the brain process information. The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurons) working in parallel to solve specific problems.

Custom defined precise recognition:

Here decision does not belong to the domain of experience, if the object hasn’t been learned. Recalling generates an error. A pre defined threshold of error is used to check the acceptability of error in recalling. If it is less than the threshold, maximum correlation is used to take the decision otherwise object will declare a new pattern.


When a system designed, several parameters available to check the quality of system like speed, power consumption, size etc. Another kind of parameter, which defines the reliability of system, is fault tolerance.
If defines the reliability of the system output if any fault happens. For a given design, to know the performance value with respect to fault tolerance, it requires to analyze the system thoroughly. ANN works on parallel distributed computing, so expectation of fault tolerance is very high. This is matter of interest to know how faults in ANN affect its performance.


To have a better understanding of ANN, it requires detail information about its internal dynamics. By selecting the various factors like hidden layer weights, outer layer weights, learning rate, error function etc, and the mechanism behind providing such an outstanding performance can be explored.
Apart from this, how improvement in performance can be done, solution can be searched through such analysis.


In practical application, after recognition some action taken place. In this project and implimentation this action taken as retrieval of information associated with that particular image. The proposed system will not only recognize the true image but also if true image has been corrupted with various types of noise. Following ways the true image will corrupt with noise.


An artificial neural network (ANN) also called neural network is an information processing paradigm that is inspired by the way biological nervous system, such as the brain process information. The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurons) working I parallel to solve problems.
ANNs, like people, learn by example. An ANN is configured for a specific application, such as pattern recognition, signal processing and data classification etc. through a learning process .

Overview of ANN

Neural network simulations appear to be a recent development. However, this field was established before the advent of computers, and has survived at least one major setback and several eras.
Many important advances have been boosted by the use of inexpensive computer emulations. Following an initial period of enthusiasm, the field survived a period of frustration and disrepute. During this period when funding and professional support was minimal, important advances were made by relatively few researchers. These pioneers were able to develop convincing technology, which surpassed the limitations identified by Minsky and Papert. They published a book (in 1969) in which they summed up a general feeling of frustration (against neural networks) among researchers, and was thus accepted by most without further analysis. Currently, the neural network field enjoys a resurgence of interest and a corresponding increase in funding .

Attached Files
.doc   Artificial Neural Networks.doc (Size: 171 KB / Downloads: 24)
seminar girl
Active In SP

Posts: 519
Joined: Aug 2012
17-08-2012, 03:12 PM

Artificial Neural Networks

.ppt   Artificial Neural Networks.ppt (Size: 399 KB / Downloads: 51)

Biological inspiration

Animals are able to react adaptively to changes in their external and internal environment, and they use their nervous system to perform these behaviours.

An appropriate model/simulation of the nervous system should be able to produce similar responses and behaviours in artificial systems.

The nervous system is build by relatively simple units, the neurons, so copying their behavior and functionality should be the solution.

Artificial neurons

The McCullogh-Pitts model:
spikes are interpreted as spike rates;
synaptic strength are translated as synaptic weights;
excitation means positive product between the incoming spike rate and the corresponding synaptic weight;
inhibition means negative product between the incoming spike rate and the corresponding synaptic weight;

Learning in biological systems

The young animal learns that the green fruits are sour, while the yellowish/reddish ones are sweet. The learning happens by adapting the fruit picking behavior.

At the neural level the learning happens by changing of the synaptic strengths, eliminating some synapses, and building new ones.

Learning in biological neural networks

The learning rules of Hebb:
synchronous activation increases the synaptic strength;
asynchronous activation decreases the synaptic strength.

These rules fit with energy minimization principles.
Maintaining synaptic strength needs energy, it should be maintained at those places where it is needed, and it shouldn’t be maintained at places where it’s not needed.

Thinking To Register

12-10-2012, 11:31 PM

this is the best seminar and presentation topic ever................n this link helps to me for report ..........
seminar tips
Super Moderator

Posts: 8,857
Joined: Oct 2012
15-10-2012, 01:36 PM

to get information about the topic"ARTIFICIAL NEURAL NETWORK" full report ppt and related topic refer the link bellow and presentation-report and presentation-report and presentation-report--2973 and presentation-ppt and presentation-report?page=3


Important Note..!

If you are not satisfied with above reply ,..Please


So that we will collect data for you and will made reply to the request....OR try below "QUICK REPLY" box to add a reply to this page
Tagged Pages: artificial neural networks seminar topics, a seminar report on neural network model for information retrieval, neural networks pdf seminar topic, seminar on artificial neural network and applications, seminar presentation on neural networks and applications for free download, artificial neural network doc file, project topics on artificial neural networks,
Popular Searches: wavelet basis, ppt on artificial neural network applications in lightning, seminar topics artificial immuine system, neural networks abstract for seminar, matlab based neural network project expert, artificial, artificial sattelite seminar report,

Quick Reply
Type your reply to this message here.

Image Verification
Please enter the text contained within the image into the text box below it. This process is used to prevent automated spam bots.
Image Verification
(case insensitive)

Possibly Related Threads...
Thread Author Replies Views Last Post
  REDTACTON A SEMINAR REPORT project girl 2 516 25-04-2016, 03:58 PM
Last Post: mkaasees
  Cut Detection in Wireless Sensor Networks pdf project girl 2 1,221 16-07-2015, 09:21 PM
Last Post: Guest
  seminar report on cyber terrorism pdf jaseelati 0 299 23-02-2015, 01:49 PM
Last Post: jaseelati
  microwind software free download jaseelati 0 250 23-02-2015, 12:47 PM
Last Post: jaseelati
  seminar report on internet of things jaseelati 0 347 29-01-2015, 04:51 PM
Last Post: jaseelati
  nano ic engine seminar report jaseelati 0 294 21-01-2015, 01:43 PM
Last Post: jaseelati
  google glass seminar report pdf jaseelati 0 319 21-01-2015, 01:41 PM
Last Post: jaseelati
  rolltop laptop seminar report jaseelati 0 265 17-01-2015, 03:15 PM
Last Post: jaseelati
  computational intelligence in wireless sensor networks ppt jaseelati 0 351 10-01-2015, 03:10 PM
Last Post: jaseelati
  credit card fraud detection using hidden markov model project download jaseelati 0 264 10-01-2015, 01:34 PM
Last Post: jaseelati