2. Three Basic Components or Entities of Artificial Neural Network Introduction | Soft Computing

2. Three Basic Components or Entities of Artificial Neural Network Introduction | Soft Computing | Machine Learning by Mahesh Huddar

The following concepts are discussed:
______________________________
The models of ANN are specified by the three basic entities namely:
1. Connections: the model’s synaptic interconnections;
2. Learning: the training or learning rules adopted for updating and adjusting the connection weights;
3. activation functions.

There exist five basic types of neuron connection architectures. They are:
single-layer feed-forward network,
multilayer feed-forward network,
single node with its own feedback,
single-layer recurrent network,
multilayer recurrent network

Parameter learning: It updates the connecting weights in a neural net.
Structure learning: It focuses on the change in network structure (which includes the number of processing elements as well as their connection types).

Activation functions in ANN
1. Identity function
2. Binary step function
3. Bipolar step function
4. Ramp function
5. Sigmoidal functions
5.1 Binary sigmoid function
5.2 Bipolar sigmoid function


********************************

4. Like, Share, Subscribe, and Don't forget to press the bell ICON for regular updates

[jivankarande]

This videos deserves more than lacks of views and surely will get it. Very well explained sir 👍🌟

[joachimguth]

Great straight lessons, with the right size.

[sahilsaksena]

thank you so much sir, I have hope for passing now