Spontaneous Concept Learning with Deep Autoencoder
- https://doi.org/10.2991/ijcis.2018.25905178How to use a DOI?
- artificial intelligence, machine learning, deep learning, unsupervised learning
In this study we investigate information processing in deep neural network models. We demonstrate that unsupervised training of autoencoder models of certain class can result in emergence of compact and structured internal representation of the input data space that can be correlated with higher level categories. We propose and demonstrate practical possibility to detect and measure this emergent information structure by applying unsupervised clustering in the activation space of the focal hidden layer of the model. Based on our findings we propose a new approach to training neural network models based on emergent in unsupervised training information landscape, that is iterative, driven by the environment, requires minimal supervision and with intriguing similarities to learning of biologic systems. We demonstrate its viability with originally developed method of spontaneous concept learning that yields good classification results while learning new higher level concepts with very small amounts of supervised training data.
- © 2018, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article under the CC BY-NC license (http://creativecommons.org/licences/by-nc/4.0/).
Cite this article
TY - JOUR AU - Serge Dolgikh PY - 2018 DA - 2018/11 TI - Spontaneous Concept Learning with Deep Autoencoder JO - International Journal of Computational Intelligence Systems SP - 1 EP - 12 VL - 12 IS - 1 SN - 1875-6883 UR - https://doi.org/10.2991/ijcis.2018.25905178 DO - https://doi.org/10.2991/ijcis.2018.25905178 ID - Dolgikh2018 ER -