# Mixture Density Network: determine the parameters of each Gaussian component

This is a good paper, but I am still confused about a few small details. I am wondering if anyone could give me some help:

1. Basically the mixing coefficient alpha_i can be computed through a softmax function in eq (25) below. However, in eq (25), what's the upper alpha for each $(z_i)^{alpha}$? Is it a free parameter to be fitted?

2. Similarly, in eq (26), what's the upper sigma in $(z_i)^{sigma}$? Is it a free parameter to be fitted as well? Thanks!

• I edited the equations due to unreadability, please check them. Aug 6, 2018 at 21:37

Actually, the upper alpha and the upper sigma are not free parameters to be set, they are just used to represent the output activations corresponding to the mixture coefficients and the variances, respectively. They are used to distinguish derivatives with respect to the alpha and sigma. I say it from page 275 of the book “pattern recognition and machine learning” by Christopher Bishop”:

• In your example, Does this mean that $(a_k)^{pi}$, $(a_{kl})^{mu}$, $(a_k)^{sigma}$ are just 3 different output variables? So does in my example, $(z_i)^{alpha}$ and $(z_i)^{sigma}$ are just two different output variables (one corresponds to the mixture coefficient, and the other one corresponds to sigma). The alpha and sigma are just variable index, am I understanding this correctly? Aug 6, 2018 at 23:16
• @Edamame Yes, they are just variable index. Aug 7, 2018 at 10:32