Using non-oscillatory dynamics to disambiguate simultaneous patterns

Simultaneous patterns within images may have conflicting interpretations depending on context (other representations concurrently inferred). This causes significant problems known as dasiathe binding problempsila and dasiathe superposition catastrophepsila for recognition algorithms that incorporate parameter optimization (including neural networks). Previously oscillatory dynamics have been proposed to better separate patterns and address such problems. Another dynamic method, independent of oscillation, is proposed that infers which representations fit together. It works by cycling activation between inputs and outputs. Inputs activate contending representations which in turn inhibit their representative inputs. Inputs utilized by multiple representations are more ambiguous and are inherently inhibited more. The inhibited inputs then affect representation activity, which again affects inputs. The cycling is repeated until a steady state is reached. This method allows simultaneous evaluation of representations and can determine what set of representations best fit the whole image. The implementation of feedback dynamics for separating patterns is described in detail and key examples are demonstrated by simulations.