Elements of a cybernetic epistemology: sequence learning systems

Abstract

Purpose -The purpose of this paper is to analyze how sequence learning can build on pattern-recognition systems and how it can contribute to the behavioral options of goal-oriented systems. Design/methodology/approach -A functional approach is used to develop the necessary cybernetic structures of a subsystem for sequence learning, that can recognize patterns, register patterns occurring repeatedly and connect these to sequences. Based on that it is analyzed how goal-oriented systems can use information about reoccurring sequences. Findings -A subsystem for sequence learning basically requires pattern recognition and it needs a structure for the directed connection of single standards for pattern matching to standards for sequences, given that it can learn both new patterns and new sequences. Such a subsystem for sequence learning may recognize a certain pattern and with that the end of a certain sequence. So it may deliver more than one output signal at a point in time, and therefore needs additionally a subsystem for directing attention. Practical implications -The paper analyses the principles of an "associative" way of connecting standards for pattern matching to standards for sequences. Also it shows the cybernetic necessity of an attention directing system that has to decide how to deal with the multiple outputs of a subsystem for sequence learning, i.e. to decide to act either towards a pattern or a whole sequence. Originality/value -The paper investigates basic mechanisms of sequence learning and its contribution to goal-oriented behavior. Also, it lays the base for an analysis of attention directing systems and anticipatory systems.

Elements of a cybernetic epistemology: elementary anticipatory systems

“…So far we showed that ranging from feedback systems via various forms of adaptive systems to learning systems using pattern recognition and sequence learning (Nechansky, 2012c). Now here we found the continuation of this necessary evolution, showing how anticipation builds on sequence learning.…”

“…As already mentioned we will consider here just temporal patterns connected via the "associative" way (Nechansky, 2012c). And we will only name some of the many internal controller functions, which enable this data processing.…”

“…We called this an "associative" connecting of observed patterns. From that we derived our definition of a sequence (Nechansky, 2012c). A sequence is an internal representation derived from unconnected standards for pattern matching {M} 1,t1 , {M} 2,t2 , {M} 3,t3 , .…”

Elements of a cybernetic epistemology: output‐side attention directing systems

“…This leads to the decision problem where to the whole system should turn its attention (towards the pattern or the sequence). We concluded that a subsystem for attention directing emerges here as a cybernetic necessity (Nechansky, 2012b).…”

“…In previous papers we analyzed the cybernetic structures of goal-orientated systems of increasing complexity, starting with feedback systems (Nechansky, 2006), via different forms of adaptive and learning systems (Nechansky, 2008(Nechansky, , 2009(Nechansky, , 2010a(Nechansky, , b, 2012a to sequence learning systems (Nechansky, 2012b). The overarching epistemological principle applied in all these investigations was that elementary decisions are goal-orientated acts following the form: if{ðdataÞ ðrelationÞ ðgoalÞ}; then {trigger for a goal -orientated action}:…”