RNN vs CNN: a beginner's point of view

When you start learning about AI in general, there's a probable knowledge roadmap you'll go through. Starting with statistics, some programming, diving into Machine Learning, and knowing about different models for different solutions, you finally reach Deep Learning, and this is where things change a bit. Yes, Deep Learning is also based on statistics and algorithms, and yes, you have to code things for them to work, but there are also different models that behave better on particular problems. Here come the well-known improvements from the traditional Neural Networks, which perform much better for certain types of data, and excel in certain tasks: Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN). But, what is the main difference between these models?