Figure 3.

Perception of “smile” and “frown” patterns in noise, an example of dynamic logic “from vague-to-crisp” process: (A) true “smile” and “frown” patterns are shown without noise; (B) actual image available for recognition (signals are below noise, signal-to-noise ratio is about 1/3); (C) an initial vague concept-model; (D) through (H) show improved concept-models at various iteration stages (total of 21 iterations). Between stages (D) and (E) DL tries to fit the data with more than one model and decided, that it needs three models to “understand” the content of the data. Until stage (G) the DL “thought” in terms of simple blob models, at (G) and beyond, the algorithm decided that it needs more complex parabolic models to describe the data. Iterations stopped at (H), when similarity (3) stopped increasing.