コジマ　　ヒロキ   Kojima Hiroki   小島　大樹    所属   千葉工業大学  デザイン＆サイエンス研究科 デザイン＆サイエンス専攻    職種   准教授
言語種別	日本語
発行・発表の年月	2022/08
形態種別	学術雑誌
標題	Organization of a Latent Space structure in VAE/GAN trained by navigation data.
執筆形態	共著
掲載誌名	Neural networks : the official journal of the International Neural Network Society
掲載区分	国外
巻・号・頁	152,234-243頁
著者・共著者	Hiroki Kojima, Takashi Ikegami
概要	We present a novel artificial cognitive mapping system using generative deep neural networks, called variational autoencoder/generative adversarial network (VAE/GAN), which can map input images to latent vectors and generate temporal sequences internally. The results show that the distance of the predicted image is reflected in the distance of the corresponding latent vector after training. This indicates that the latent space is self-organized to reflect the proximity structure of the dataset and may provide a mechanism through which many aspects of cognition are spatially represented. The present study allows the network to internally generate temporal sequences that are analogous to the hippocampal replay/pre-play ability, where VAE produces only near-accurate replays of past experiences, but by introducing GANs, the generated sequences are coupled with instability and novelty.
DOI	10.1016/j.neunet.2022.04.012
ISSN	1879-2782
PMID	35561527