Artificial Neural Networks - class-www\engineering

muscleblouseAI and Robotics

Oct 19, 2013 (4 years and 2 months ago)

83 views

Rohit

Ray

ESE 251


What are Artificial Neural
Networks?


ANN are inspired by models of the biological nervous
systems such as the brain


Novel structure by which to process information


Number of highly interconnected processing elements
(neurons) working in unison to solve specific
problems.


Recent Development


First artificial neuron
-
1943 by Warren McCulloch and
Walter Pits.


But the technology available at that time did not allow
them to do too much.


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 behaviour and functionality
should be the solution.


From http://www.scienceclarified.com/scitech/Artificial
-
Intelligence/Mind
-
Versus
-
Metal.html

Artificial Neural Networks (ANNs),


Work in the same way as the brain's neural network.


An artificial neuron has a number of connections or inputs.


It is based on the belief that the way the brain works is all
about making the right connections



Are good for prediction and estimation when:



Inputs are well understood


Output is well understood


From http://www.scienceclarified.com/scitech/Artificial
-
Intelligence/Mind
-
Versus
-
Metal.html

Artificial Neuron

From
http://www.uic.edu/classes/idsc/ids572cna/Neural%20Networks_1
.pdf

Example of a ANN

How does it work


Neural Network Training


Training
-

process of setting the best weights on the
edges connecting all the units in the network


Use the training set to calculate weights such that ANN
output is as close as possible to the desired output for as
many of the examples in the training set as possible

Training an ANN


Adjust weights such that the application of inputs produce desired


outputs (as close as possible)



Input data is continuously applied, actual outputs calculated, and
weights are adjusted


Weights should converge to some value after many rounds of training


Supervised training


Adjust weights such that differences between desired and actual outputs
are minimized


Desired output: dependent variable in training data


Each training example specifies {independent variables, dependent
variable}


Unsupervised training


No dependent variable specified in training data


Train the NN such that similar input data should generate same output

From
http://www.uic.edu/classes/idsc/ids572cna/Neural%20Networks_1
.pdf

Example: Will the teacher give a quiz?



To help solve this question a programmer is provided with the following options


The teacher loves giving quizzes = 0.2.


The teacher has not given a quiz in two weeks = 0.1.


The teacher gave the last three quizzes on Fridays = 0.3.



The sum of the input weights equals 0.6.



The threshold assigned to that neuron is 0.5. In this case, the net value of the neuron exceeds the
threshold number so the artificial neuron is fired. This process occurs again and again in rapid
succession until the process is completed.



If the ANN is wrong, and the teacher does not give a quiz on Friday, then the weights are lowered.


Each time a correct connection is made, the weight is increased. The next time the question is asked,
the ANN will be more likely to answer correctly.



The proper connections are weighted so that there is more chance that the machine will choose that
connection the next time. After hundreds of repeated training processes, the correct neural network
connections are strengthened and remembered, just like a memory in the human brain


A computer can make millions of trial
-
and
-
error attempts at lightning speed.





http://www.scienceclarified.com/scitech/Artificial
-
Intelligence/Mind
-
Versus
-
Metal.html#ixzz0V6k2i38h

Comparison to other methods


Simulated Annealing


More accurate results


Much slower


Genetic Algorithms


More accurate results


Slower


Application of ANNs


Broad applicability to real world business problems.


Since neural networks are best at identifying patterns
or trends in data, they are well suited for prediction or
forecasting needs including:


sales forecasting


industrial process control


customer research


data validation


Risk management


target marketing


Application Cont.


Medicine


Recognizing diseases from various scans


no need to provide a specific algorithm on how to identify the
disease


Modeling Parts of the Human body


cardiovascular system must mimic the relationship among
physiological variables (i.e., heart rate, systolic and diastolic
blood pressures, and breathing rate)


specific to an individual (physical condition)


Instant Physician(1980’s)


Given a set of symptoms it will then find the full stored pattern
that represents the "best" diagnosis and treatment.






Conclusion


Computing world lots to gain from ANNs


Ability to learn by example makes them very flexible and
powerful


no need to devise an algorithm in order to perform a
specific task; i.e. there is no need to understand the
internal mechanisms of that task


Regularly used in medicine and business


Used to make models


Find optimums, recognize patterns

Works Cited


http://www.scienceclarified.com/scitech/Artificial
-
Intelligence/Mind
-
Versus
-
Metal.html


http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol
4/cs11/report.html


http://www.uic.edu/classes/idsc/ids572cna/Neural
%20Networks_1.pdf