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.


    Access

    Download


    Export, share and cite



    Title :

    SPONTANEOUS CATEGORIZATION AND SELF-LEARNING WITH DEEP AUTOENCODER MODELS


    Contributors:


    Publication date :

    2019




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown




    Learning Compositional Categorization Models

    Ommer, B. / Buhmann, J. M. | British Library Conference Proceedings | 2006


    Categorization of On Road Automobiles using Deep Learning Approach

    J, Aiswarya / K, Veerappan / K, Mariammal | IEEE | 2022


    Deep Feature Consistent Variational Autoencoder

    Hou, Xianxu / Shen, Linlin / Sun, Ke et al. | ArXiv | 2016

    Free access

    NVAE: A Deep Hierarchical Variational Autoencoder

    Vahdat, Arash / Kautz, Jan | ArXiv | 2020

    Free access

    Movie Recommendation System Using Deep Autoencoder

    Srikanth, Purushothaman / Ushitaasree, E. / Bhargav Bhattaram, Sai Mani et al. | IEEE | 2021