# Organization of a Latent Space structure in VAE/GAN trained by navigation data

arXiv: https://arxiv.org/abs/2102.01852 · HTML: https://mlsanity.com/paper/2102.01852/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 48 references that are in the map.
- First posted on arXiv 3 Feb 2021.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [Stochastic Variational Video Prediction](https://mlsanity.com/paper/1710.11252/) (2017)
- [Stochastic Adversarial Video Prediction](https://mlsanity.com/paper/1804.01523/) (2018)
- [A Review on Deep Learning Techniques for Video Prediction](https://mlsanity.com/paper/2004.05214/) (2020)

## Built on by (most cited first, 2 of 2)

- [Can We Leave Deepfake Data Behind in Training Deepfake Detector?](https://mlsanity.com/paper/2408.17052/) (2024)
- [Multimodal hierarchical Variational AutoEncoders with Factor Analysis latent space](https://mlsanity.com/paper/2207.09185/) (2022)

## Abstract (arXiv)

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.