The link function provides the relationship between the linear predictor and the mean of the distribution function. There are many commonly used link functions, and their choice can be somewhat arbitrary. It makes sense to try to match the domain of the link function to the range of the distribution function's mean.
When using a distribution function with a canonical parameter heta, the canonical link function is the function that expresses heta in terms of mu, i.e. heta = b(mu). For the most common distributions, the mean mu is one of the parameters in the standard form of the distribution's density function, and then b(mu) is the function as defined above that maps the density function into its canonical form. When using the canonical link function, b(mu) = heta = mathbf{X}oldsymbol{eta}, which allows mathbf{X}^{
m T} mathbf{Y} to be a sufficient statistic for oldsymbol{eta}.
Following is a table of several exponential-family distributions in common use and the data they are typically used for, along with the canonical link functions and their inverses (sometimes referred to as the mean function, as done here).