Please enable JavaScript.
Coggle requires JavaScript to display documents.
Neural Networks (Applications (Aerospace (Autopilot aircrafts, aircraft…
Neural Networks
Applications
Aerospace
Autopilot aircrafts, aircraft fault detection.
Automotive
Automobile guidance systems.
Military
Weapon orientation and steering, target tracking, object discrimination, facial recognition, signal/image identification.
Electronics
Code sequence prediction, IC chip layout, chip failure analysis, machine vision, voice synthesis.
Financial
Real estate appraisal, loan advisor, mortgage screening, corporate bond rating, portfolio trading program, corporate financial analysis, currency value prediction, document readers, credit application evaluators.
Industrial
Manufacturing process control, product design and analysis, quality inspection systems, welding quality analysis, paper quality prediction.etc...
Medical
Cancer cell analysis, EEG and ECG analysis, prosthetic design, transplant time optimizer.
Telecommunications
Image and data compression, automated information services, real-time spoken language translation.
Transportation
Truck Brake system diagnosis, vehicle scheduling, routing systems.
Software
Pattern Recognition in facial recognition, optical character recognition, etc.
Machine learning
Supervised Learning
It involves supervisor to teach machine by feeding the examples data to which answer is known by supervisor.
Unsupervised Learning
It is required when there is no example data set with known answers. For example, searching for a hidden pattern.
Reinforcement Learning
This strategy is build on observation, ANN makes decision by observing its environment.
Types of Artificial Neural Networks.
FeedForward ANN
Information flows in only one direction without feedback. They have fixed inputs and outputs.
FeedBack ANN
Feedback loop is allowed, they are used in content addressable memories.
Bayesian Networks (BN)
These are the graphical structures used to represent the probabilistic relationship among a set of random variables. Bayesian networks are also called Belief Networks or Bayes Nets. BNs reason about uncertain domain.
The BN variables are composed of two dimensions.
Range of prepositions
Probability assigned to each of the prepositions.
Building a Bayesian Network
Example. Lungs Cancer
Gather Relevant Information of Problem.
Is the patient a smoker? If yes, then high chances of cancer and bronchitis.
Is the patient exposed to air pollution? If yes, what sort of air pollution?
Take an X-Ray positive X-ray would indicate either TB or lung cancer.
Common types of discrete nodes
Boolean nodes
They represent propositions, taking binary values TRUE (T) and FALSE (F).
Ordered values
A node Pollution might represent and take values from {low, medium, high} describing degree of a patient’s exposure to pollution.
Integral values
A node called Age might represent patient’s age with possible values from 1 to 120. Even at this early stage, modeling choices are being made.
What is Artificial Neural Network ANN?
Dr. Robert Hecht-Nielsen "...a computing system made up of a number of simple, highly interconnected processing elements, which process information by their dynamic state response to external inputs.”
Back Propagation Algorithm
It is learning or training algorithm which learns by examples, Back Propagation networks are ideal for simple Pattern Recognition and Mapping Tasks.