In Quantum-Chemical Insights from Deep Tensor Neural Networks, I would like to ask a question about how to initialize the coefficient vector of the network, because I could not understand it even after reading the paper. In the paper, it says
All presented models use atomic descriptors with 30 coefficients. We initialize each coefficient randomly
If it is initialized randomly like this, why do we initialize it randomly since we cannot use the information of nuclear charge as mentioned in the paper?