Addressing this question from a computational point of view, research into machine learning has shed a lot of light on the questions concerning the prerequisites of learning. In particular, the No Free Lunch Theorem is the result of an attempt to quantify the amount of prior knowledge required for extracting information from data. This theorem is defined as follows:
"The No Free Lunch Theorem Of Optimization (NHI) is an impossibility theorem telling us that a general-purpose universal optimization strategy is impossible, and the only way one strategy can outperform another is if it is specialized to the structure of the specific problem under consideration." Yu-Chi Ho, Simple explanation of the no free lunch theorem of optimization
This definition might be formalized in logical notation as follows:
- Sxz = x is a strategy for a problem of type z
- P(x) = the performance of x
- Cxz = x is specialized to problems of type z
∀xyz[(Sxz & Syz & P(x) > P(y)) → Cxz]
From this, it's fairly easy to conclude the following:
∀xz[(~Cad & Sad & P(a) > 0) → ~Ǝy[Syd & P(y) = 0]]
Translation: Without any prior knowledge of a given type of problem, if a strategy for that type can be expected to be successful, it must be assumed that there exists no strategy of the same type that consistently fails.
Therefore, from a purely empirical perspective, it must be concluded that if there are any types of problems for which generic strategies consistently fail, the initial stages of learning must not be of such a type. Otherwise, empiricism is false.
That really is a huge assumption to make when it's remembered that all machine learning programs have certain assumptions programmed into them. The designers of such systems don't expect the machine to learn, for example, that data contains information or that concepts can be extracted by comparisons and other logical operations. In other words, there is no such thing as a purely empirical AI program because they are always hard coded with some basic a priori knowledge.
Consequently, it's unimaginable what such a generic strategy could possibly mean if it is supposed that it consists of none of the assumptions hard-coded into current machine learning programs.