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

• URL: http://arxiv.org/abs/2102.01852v1
• Date: Wed, 3 Feb 2021 03:13:26 GMT
• Title: Organization of a Latent Space structure in VAE/GAN trained by navigation data
• Authors: Hiroki Kojima and Takashi Ikegami
• Abstract summary: We present a novel artificial cognitive mapping system using generative deep neural networks (VAE/GAN) We show that the distance of the predicted image is reflected in the distance of the corresponding latent vector after training. The present study allows the network to internally generate temporal sequences analogous to hippocampal replay/pre-play.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a novel artificial cognitive mapping system using generative deep neural networks (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 constructed to reflect the proximity structure of the data set, and may provide a mechanism by which many aspects of cognition are spatially represented. The present study allows the network to internally generate temporal sequences analogous to hippocampal replay/pre-play, where VAE produces only near-accurate replays of past experiences, but by introducing GANs, latent vectors of temporally close images are closely aligned and sequence acquired some instability. This may be the origin of the generation of the new sequences found in the hippocampus.

Related papers

• Exploring Geometric Deep Learning For Precipitation Nowcasting [28.44612565923532]
  We propose a geometric deep learning-based temporal Graph Convolutional Network (GCN) for precipitation nowcasting. The adjacency matrix that simulates the interactions among grid cells is learned automatically by minimizing the L1 loss between prediction and ground truth pixel value. We test the model on sequences of radar reflectivity maps over the Trento/Italy area.
  arXiv  Detail & Related papers  (2023-09-11T21:14:55Z)
• Pose-Graph Attentional Graph Neural Network for Lidar Place Recognition [16.391871270609055]
  This paper proposes a pose-graph attentional graph neural network, called P-GAT. It compares keynodes between sequential and non-sequential sub-graphs for place recognition tasks. P-GAT uses the maximum spatial and temporal information between neighbour cloud descriptors.
  arXiv  Detail & Related papers  (2023-08-31T23:17:44Z)
• Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction [60.60223171143206]
  Trajectory prediction is a crucial undertaking in understanding entity movement or human behavior from observed sequences. Current methods often assume that the observed sequences are complete while ignoring the potential for missing values. This paper presents a unified framework, the Graph-based Conditional Variational Recurrent Neural Network (GC-VRNN), which can perform trajectory imputation and prediction simultaneously.
  arXiv  Detail & Related papers  (2023-03-28T14:27:27Z)
• Probing neural representations of scene perception in a hippocampally dependent task using artificial neural networks [1.0312968200748116]
  Deep artificial neural networks (DNNs) trained through backpropagation provide effective models of the mammalian visual system. We describe a novel scene perception benchmark inspired by a hippocampal dependent task. Using a network architecture inspired by the connectivity between temporal lobe structures and the hippocampus, we demonstrate that DNNs trained using a triplet loss can learn this task.
  arXiv  Detail & Related papers  (2023-03-11T10:26:25Z)
• iSDF: Real-Time Neural Signed Distance Fields for Robot Perception [64.80458128766254]
  iSDF is a continuous learning system for real-time signed distance field reconstruction. It produces more accurate reconstructions and better approximations of collision costs and gradients.
  arXiv  Detail & Related papers  (2022-04-05T15:48:39Z)
• Revealing Disocclusions in Temporal View Synthesis through Infilling Vector Prediction [6.51882364384472]
  We study the idea of an infilling vector to infill by pointing to a non-disoccluded region in the synthesized view. To exploit the structure of disocclusions created by camera motion during their infilling, we rely on two important cues, temporal correlation of infilling directions and depth.
  arXiv  Detail & Related papers  (2021-10-17T12:11:34Z)
• Continual Neural Mapping: Learning An Implicit Scene Representation from Sequential Observations [24.354073167898555]
  We make a further step towards continual learning of the implicit scene representation directly from sequential observations. We show for the first time that a single network can represent scene geometry over time continually without catastrophic forgetting.
  arXiv  Detail & Related papers  (2021-08-12T16:57:29Z)
• Continuity-Discrimination Convolutional Neural Network for Visual Object Tracking [150.51667609413312]
  This paper proposes a novel model, named Continuity-Discrimination Convolutional Neural Network (CD-CNN) for visual object tracking. To address this problem, CD-CNN models temporal appearance continuity based on the idea of temporal slowness. In order to alleviate inaccurate target localization and drifting, we propose a novel notion, object-centroid.
  arXiv  Detail & Related papers  (2021-04-18T06:35:03Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)
• A Prospective Study on Sequence-Driven Temporal Sampling and Ego-Motion Compensation for Action Recognition in the EPIC-Kitchens Dataset [68.8204255655161]
  Action recognition is one of the top-challenging research fields in computer vision. ego-motion recorded sequences have become of important relevance. The proposed method aims to cope with it by estimating this ego-motion or camera motion.
  arXiv  Detail & Related papers  (2020-08-26T14:44:45Z)
• Supporting Optimal Phase Space Reconstructions Using Neural Network Architecture for Time Series Modeling [68.8204255655161]
  We propose an artificial neural network with a mechanism to implicitly learn the phase spaces properties. Our approach is either as competitive as or better than most state-of-the-art strategies.
  arXiv  Detail & Related papers  (2020-06-19T21:04:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.