First page Back Continue Last page Overview Graphics

Single Layer with Bias

N1

...

input

input

Nk

...

input

input

Nk+1

...

output

B

1

If two data clusters (classes) can be separated by a decision boundary in the form of a linear equation

they are called linearly separable.

Otherwise, i.e. if such a decision boundary does not exist, the two classes are called linearly inseparable. In this case, we cannot use a simple neural network.

For this purpose, we need neural networks with bias nodes, like the one in the following diagram.

The equation looks like this: