Figure 5.

ART search and learning cycle. This figure summarises how ART searches for and learns a new recognition category using cycles of match-induced resonance and mismatch-induced reset due to interactions of an attentional system and an orienting system. (a) Input pattern I is instated across feature detectors at level F₁ of the attentional system as an activity pattern X, at the same time that it generates excitatory signals to the orienting system A with a gain ρ that is called the vigilance parameter. The activity pattern X is represented by a shaded region in (a) and (d). Activity pattern X generates inhibitory signals to the orienting system A as it generates a bottom-up input pattern S to the category level F₂. A dynamic balance within A between excitatory inputs from I and inhibitory inputs from S keeps A quiet. The bottom-up signals in S are multiplied by learned adaptive weights to form the input pattern T to F₂. The inputs T are contrast-enhanced and normalised within F₂ by recurrent lateral inhibitory signals that obey the membrane equations of neurophysiology, otherwise called shunting interactions (see section 3.15). This competition leads to selection and activation of a small number of cells within F₂ that receive the largest inputs. The chosen cells represent the category Y that codes for the feature pattern at F₁. In this figure, a winner-take-all category is chosen, represented by a single cell (population). (b) The category activity Y generates top-down signals U that are multiplied by adaptive weights to form a prototype, or critical feature pattern, V that encodes the expectation that the active F₂ category has learned for what feature pattern to expect at F₁. This top-down expectation input V is added at F₁ cells using the ART Matching Rule, whereby object attention activates a top-down, modulatory on-centre, off-surround network. If V mismatches I at F₁, then a new STM activity pattern X* (the grey pattern in (b) and (c); white regions represent inhibited cells) is selected at cells where the patterns match well enough. In other words, X* is active at I features that are confirmed by V. Mismatched features (white area) are inhibited. When X changes to X*, total inhibition decreases from F₁ to A. (c) If inhibition decreases sufficiently, the orienting system A releases a nonspecific arousal burst to F₂; that is, ‘novel events are arousing’. Within the orienting system A, a vigilance parameter ρ determines how bad a match will be tolerated before a burst of nonspecific arousal is triggered. This arousal burst triggers a memory search for a better-matching category, as follows: arousal resets F₂ by inhibiting Y. (d) After Y is inhibited, X is reinstated and Y stays inhibited as X activates a different winner-take-all category Y*, at F₂. Search continues until a better matching, or novel, category is selected. When search ends, a feature-category resonance triggers learning of the attended data in adaptive weights within both the bottom-up and top-down pathways, at the same time that it supports conscious recognition of the attended object (Grossberg, 2013a, 2017b). As learning stabilises, inputs I can activate their globally best-matching categories directly through the adaptive filter, without activating the orienting system.

Source: Adapted with permission from Carpenter and Grossberg (1987).