Not understand the concept of bias

here what are bias and its use ? why we are adding to each layer for the final answer?

hi @kushal1998
Bias allows you to shift the activation function by adding a constant (i.e. the given bias) to the input. Bias in Neural Networks can be thought of the role of a constant in a linear function, whereby the line is effectively transposed by the constant value.
like u are trying to fit line y = m*x + c without knowing c (bias) u cant fit the line
similarly without bias u cant provide the shift to activations