Representation is how a model is formally constructed in a way which a computer can interpret. Examples are decision trees, support vector machines, and neural nets. ML models are commonly referred to by the name of the representation. A classifier is an instance in the set of possible models generated by the representation. When you make the choice of which representation to use, you are determining the possibilities of classifiers that your model is able to learn. The range of possibilities is known as the hypothesis space.

If the true (and remember, unknown) classifier model is not in the hypothesis space, it cannot be learned. Most representation models you will use have a large hypothesis space, so this is probably not going to be a problem. But you should be aware of it, as you may need to expand your choices of representation models in order to expand the collective hypothesis space. This may be necessary if you are getting poor predictive performance from your normal go-to set of ML models.