"Feedback is the control of a system by reinserting into the system the results of its performance. If these results are merely used as numerical data for criticism of the system and its regulation, we have the simple feedback of the control engineer. If, however, the information which proceeds backwards from the performance is able to change the general method and pattern of the performance, we have a process which may very well be called learning." (Norbert Wiener, "The Human Use of Human Beings: Cybernetics and Society", 1954)
"In general, this term is used to describe systems or inputs where the current output or state can modify the effect of input. A positive feedback acts as an amplifier or magnifier on the output (e.g., the rich get richer and the poor get poorer). A negative feedback acts to diminish large inputs and magnify small inputs. This becomes important in keeping a system in control or 'on target'." (William J Raynor Jr., "The International Dictionary of Artificial Intelligence", 1999)
"set of signals connected from the output terminals to some input terminals." (Teuvo Kohonen, "Self-Organizing Maps" 3rd Ed., 2001)
"The process in which part of the output of a system is returned to its input in order to regulate its further output. Often this is done intentionally, in order to control the dynamic behavior of the system." (Moti Frank, "Active Learning and Its Implementation for Teaching", 2008)
"The return of a portion of the output of a process or system to the input, especially when used to maintain performance or to control a system or process." (Dino Ruta, "Organizational Implications of Managing the HRIS Employee Experience", 2009)
"Connections that travel backward in a neural network from higher to lower layers creating a loop in the network that allows signals to circulate within it." (Terrence J Sejnowski, "The Deep Learning Revolution", 2018)
"when the effect of a causal impact comes back to influence the original cause of that effect." (David N Ford, "A system dynamics glossary", System Dynamics Review Vol. 35 (4), 2019)
"it is the process that allows to have information of one variable on another or others, during the simulation and not at the end, this allows to adjust on the model to modify, if it were the case, possible decisions that do not affect the desired result by the organization." (Ernesto A Lagarda-Leyva & Ernesto A Vega-Telles, "Application of System Dynamics in a Gasoline Service Station: Decision Making Using Graphical Interface", 2020)
No comments:
Post a Comment