In this studythe author investigates information processing in deep autoencoder models. It is demonstrated that unsupervised training of autoencoders of certain class can result in emergence of compact and structured internal representations of the input data space that can be correlated with higher level categories. The authors propose and demonstrate the practical possibility to detect and measure this emergent information structure by applying unsupervised density clustering in the activation space of the focal hidden layer of the model. Based on the findings of the studya new approach to training neural network models is proposed that is based on the emergent in unsupervised training information landscape, that is iterative, driven by the environment, requires minimal supervision and with interesting similarities to learning of biologic systems. In conclusion, a discussion of theoretical foundations of spontaneous categorization in self-learning systemsis provided.
SPONTANEOUS CATEGORIZATION AND SELF-LEARNING WITH DEEP AUTOENCODER MODELS
2019
Aufsatz (Zeitschrift)
Elektronische Ressource
Unbekannt
Metadata by DOAJ is licensed under CC BY-SA 1.0
Learning Compositional Categorization Models
British Library Conference Proceedings | 2006
|Movie Recommendation System Using Deep Autoencoder
IEEE | 2021
|VISUALIZATION OF DRIVING BEHAVIOR USING DEEP SPARSE AUTOENCODER
British Library Conference Proceedings | 2014
|