I have searched various sources to find out what distinguishes the McCulloch-Pitts neuron from the perceptron invented by Rosenblatt. In most sources only one of these elements is considered, in others they are used as synonyms. Can someone explain the differences in how they work?
MP model : 1) inputs are binary values; 2) has not weights
Rosenblatt model: 1) inputs can take any real numbers; 2) has weights.
About weights in the MP model. Actually there are weights in this model. But the model has not a method to train them. And so these weights are fixed.
About Rosenblatt model. It has weights and a method to adjust them.
In some literature the weights from MP model is called "pseudo-weights" because actually a model has them (for calculating weighted sum) but has not method to train them.