Applications of Artificial Neuron Network ANN
Applications of Artificial Neuron Network ANN
Network of Artificial neurons:
Besides the simple neuron architecture there exists several other types of neural Network connections. The arrangement of neurons to form layers and the connection patterns formed within and between layers is called the network architecture. There exist 5 basic types of neuron
Artificial Neuron Network
connection types which are:
- Single-layer-feed-forward networks
- Multilayer-feed-forward-networks
- Single node with its own feedback
- Single-layer recurrent networks
- Multilayer recurrent Network.
SINGLE LAYER NETWORK: It is formed by taking a processing element and combining it with other processing elements. Practically a layer implies a stage, going stage by stage, i.e the input stage and the output stage is linked with each other. These linked interconnections lead to the formation of various Network architectures. When a layer is formed, the inputs can be connected to these nodes with various weights, resulting in a series of outputs, one per node. In this way a single layer network is formed.
PERCEPTRON NETWORK: Perceptron networks come under single-layer-feed-forward networks. Various types of perceptron were designed by Rosenblatt (1962), and Minsky-parpert(1969, 1988)
Perceptron training algorithm
Step 0: Initialize the weight and bais (for easy calculation they can be set to zero). Also initialize the learning rate α(0<α<1). For simplicity α is set to 1.
Step1: perform steps 2-6 until the final stopping condition is false.
Step2: perform steps 3-5 for each training pair indicated by s:t
Step3: the input layer containing input units is applied with identity activation functions.
Step4: calculate the output of the network. To do so first obtain the net input.
Where “n” is the number of input neurons in the input layer. Then apply the activations over the net input calculated to obtain the output.
Step5: weight and bais adjustment: compare the value of the actual (calculated) output and desired (target) output.
If y ≠ t, then
xi (new) = xi (old) + tαxi
b (new) =b (old) +αt
else we have:
xi (new) = xi (old)
b (new) = b (old)
Step6: train the network until there is no weight change. This is the stopping condition for the network. If this condition is not met, then again start from step2.
LINEAR SEPARABILITY:
An ANN does not give an exact solution for a non-linear problem. However, it provides possible solutions to nonlinear problems. Linear separability is the concept wherein the separation of the input space into regions is based on whether the network response is positive or negative.
A decision line is drawn to separate positive or negative responses, the decision line may also be called as the decision making line or linear separable line. The necessity of the linear separability concept was felt to classify the patterns based on their output response.
Also can visit:
Tell us Your Queries, Suggestions and Feedback
One Response to Applications of Artificial Neuron Network ANN
« Image Processing , Substraction and Averaging FORMATION OF Z BUS MATRIX »
n machine learning and computational neuroscience, an artificial neural network, often just named a neural network, is a mathematical model inspired by biological neural networks.Have a look on this article.