Can neurons in Hopfield Network have non-binary values ( continuous values instead of -1 and +1)? If they can , is energy expression for hopfield NN stays the same? What is the main condition for Hopfield energy to stay consistent? I am aksing this particularly because I am wondering if we could consider a text as a Hopfield Network where word occurence frequencies in the text could be neuron states.(so the neuron state would be x>1). I am wondering if energy of Hopfield NN could work in this case.