1. Characteristics
- Neural Network is composed of elements that are analogous to the most elementary function of the biological neuron. They learn from experience, generalize from previous examples to new ones, and abstract essential characteristics from inputs containing irrelevant data.
2. Structures
- A set of input is applied, each representing the output of another neuron. Each input is multiplied by a corresponding weight, analogous to a synaptic strength, and all of the weighted inputs are then summed to determine the activation level of the neuron.
- Each neuron is linked to its neighbors with varying coefficients of connectivity that represent the strengths of these connections. Learning is accomplished by adjusting these strengths to cause the overall network to output appropriate results.
- All artificial neural network have a similar topology. Some neurons interface the real world in order to receive their input and others provide the real world with the network¡¯s outputs. All the rest of the neurons are hidden from view.
3. Learning
- Neural network is sometimes called machine learning algorithm, because changing of its connection weights (training) causes the network to learn the solution to a problem. The strength of connection between the neurons is stored as a weight-value for the specific connection. The system learns new knowledge by adjusting these connection weights.
4. Design of Neural Network
- Arrange neurons in various layers.
- Decide the type of connection among neurons for different layers, as well as among the neurons within a layer.
- Decide the way a neuron receives input and produces output.
- Determine the strength of connection within the network by allowing the network to learn the appropriate values of connection weights by using a training data set.
5. Applications
- Prediction
- e.g. pick the best stocks in the market, predict weather, and identify people with cancer risk.
- Classification
- Use input value to determine the classification.
- e.g. is the input the letter A, is the blob of the video data a plane and what kind of plane is it.
- Data association
- Like classification but it also recognizes data that contains errors.
- e.g. not only identify the characters that were scanned but identify when the scanner is not working properly.
- Data Conceptualization
- Analyze the input so that relationship between groups can be inferred.
- e.g. extract from database the names of those most likely to buy a particular product.
- Data Filtering
- Smooth an input signal. e.g. take the noise out of a telephone signal.
6. References :
"Artificial Neural Networks" ;
(http://www.hj.se/~de96klda/NeuralNetworks.htm)
"Neural Computing-Theory and Practice" - Philip D. Wasserman
