Professional Documents
Culture Documents
Types of NN and Learning
Types of NN and Learning
Types of NN and Learning
NEURON
CONNECTION
ARCHITECTUR
E
LEARNING
Basic types of neuron connection architectures
The arrangement of neuron to form layer and the connection pattern form within and between layer is
called network architecture
• Single-layer feed-forward network;
• Multilayer feed-forward network;
• single node with itS own feedback;
• Single-layer recurrent network;
• Mulrilayer recurrent network.
Description
Feedforward network: If no neuron in the output layer is an input to the node in same layer or its
preceding layers.
Feedback network: When output can be directed back as input to same or preceding layers nodes
Fully connected networks: Every output from one layer is connected to each and every node in the
next layer
Lateral Feedback: If the output of the processing element is directed back as input to processing
elements in the same layer
Recurrent Neural Network: Feedback network with closed loop.
Competitive Layer: They have fixed weight of This net is called Maxnet. unsupervised learning
network
Disadvantage of FFNN
Two types
1. Parameter learning: It updates the connecting weights in a neural net.
2. Strncture learning: It focuses on the change in network structure (which includes the number of processing
elements as well as their connection types).
• Wij is the weight from processing element “i" (source node) to processing element "j' (destination node).
Bias
• The bias included in the network has its impact in calculating the net input. The bias is included by adding a
component x0= 1 to the input vector X, the input vector becomes
Learning rate
It is used to control amount of weight adjustment at each step of training, the learning rate ranges from 0 to 1,
determines rate of learning at each time stamp.