Anda di halaman 1dari 14

Yasser Al-Zahrani Abdullah Al-Fifi Abdullah Al-Ammari

What is the Neural Network ?
Why we use ANN ? What can a ANN do?

Where to use ANN ?

What is ANN? Application (Back-propagation Algorithm).

Short Program video.

Neural Network
The term neural network was traditionally used to refer to a network or circuit of biological neurons. The modern usage of the term often refers to artificial neurons networks, which are composed of artificial neurons or nodes.

Neurone vs. Node

Synapse vs. weight

Why we use ANN ?

Neural networks, with their remarkable ability to derive

meaning from complicated or imprecise data, can be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques.
A trained neural network can be thought of as an "expert"

in the category of information it has been given to analyze.

What can a ANN do?

Compute a known function. Approximate an unknown function. Pattern Recognition. Signal Processing.

Where to use ANN ?

Detection of medical phenomena. A variety of health-related

indices (e.g., heart rate, respiration rate) can be monitored. Stock market prediction. Fluctuations of stock prices and stock indices are another example. Credit assignment. A variety of pieces of information are usually known about an applicant for a loan. Monitoring the condition of machinery. Neural networks can be instrumental in cutting costs by bringing additional expertise to scheduling the preventive maintenance of machines. Engine management. Neural networks have been used to analyze the input of sensors from an engine.

What is ANN ?
A set of nodes (units, neurons, processing elements).

1. Each node has input and output. 2. Each node performs a simple computation by its node function. There are weighted connections between nodes. What can be computed by a neural network is primarily determined by the connections and their weights.

Back-propagation Algorithm.

Wnew = Wold + () (desired output) input

Learning rate is one of the parameters which governs how fast a neural network learns and how effective the training is. :Learning rate is a value ranging from zero to unity. Choosing a value very close to zero, requires a large number of training cycles. This makes the training process extremely slow.


Sample Example

Presentations: Artificial Neural Networks by Torsten Reil Artificial Neural Networks by Shikhir Kadians group An Introduction to Neural Networks by Vincent Cheung and Kevin Cannons Web: Neural Networks report by Christos stergiou and Dimitios Siganos