Probability matching in perceptrons: Effects of conditional dependence and linear nonseparability

Probability matching occurs when the behavior of an agent matches the likelihood of occurrence of events in the agent's environment. For instance, when artificial neural networks match probability, the activity in their output unit equals the past probability of reward in the presence of a stim...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	PloS one 2017-02, Vol.12 (2), p.e0172431-e0172431
Hauptverfasser:	Dawson, Michael R W, Gupta, Maya
Format:	Artikel
Sprache:	eng
Schlagworte:	Analysis Artificial neural networks Biology and Life Sciences Computer and Information Sciences Computer simulation Conditioned stimuli Contingency tables Cues Data analysis Humans Learning Matching Medicine and Health Sciences Neural networks Neural Networks (Computer) Perception Perceptrons Performance prediction Physical Sciences Physiological psychology Probability Reinforcement Reinforcement (Psychology) Research and Analysis Methods Signaling Simulation Social Sciences
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!