Probabilistic Autoencoder using Fisher Information

• URL: http://arxiv.org/abs/2110.14947v1
• Date: Thu, 28 Oct 2021 08:33:24 GMT
• Title: Probabilistic Autoencoder using Fisher Information
• Authors: Johannes Zacherl (1 and 2), Philipp Frank (1 and 2) and Torsten A. En{\ss}lin (1 and 2) ((1) Max-Planck Institut f\"ur Astrophysik (2) Ludwig-Maximilians-Universit\"at M\"unchen)
• Abstract summary: In this work, an extension to the Autoencoder architecture is introduced, the FisherNet. In this architecture, the latent space uncertainty is not generated using an additional information channel in the encoder, but derived from the decoder, by means of the Fisher information metric. We can show experimentally that the FisherNet produces more accurate data reconstructions than a comparable VAE and its learning performance also apparently scales better with the number of latent space dimensions.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural Networks play a growing role in many science disciplines, including physics. Variational Autoencoders (VAEs) are neural networks that are able to represent the essential information of a high dimensional data set in a low dimensional latent space, which have a probabilistic interpretation. In particular the so-called encoder network, the first part of the VAE, which maps its input onto a position in latent space, additionally provides uncertainty information in terms of a variance around this position. In this work, an extension to the Autoencoder architecture is introduced, the FisherNet. In this architecture, the latent space uncertainty is not generated using an additional information channel in the encoder, but derived from the decoder, by means of the Fisher information metric. This architecture has advantages from a theoretical point of view as it provides a direct uncertainty quantification derived from the model, and also accounts for uncertainty cross-correlations. We can show experimentally that the FisherNet produces more accurate data reconstructions than a comparable VAE and its learning performance also apparently scales better with the number of latent space dimensions.

Related papers

• Positional Encoder Graph Quantile Neural Networks for Geographic Data [4.277516034244117]
  We introduce the Positional Graph Quantile Neural Network (PE-GQNN), a novel method that integrates PE-GNNs, Quantile Neural Networks, and recalibration techniques in a fully nonparametric framework. Experiments on benchmark datasets demonstrate that PE-GQNN significantly outperforms existing state-of-the-art methods in both predictive accuracy and uncertainty quantification.
  arXiv  Detail & Related papers  (2024-09-27T16:02:12Z)
• Understanding Encoder-Decoder Structures in Machine Learning Using Information Measures [10.066310107046084]
  We present new results to model and understand the role of encoder-decoder design in machine learning (ML) We use two main information concepts, information sufficiency (IS) and mutual information loss (MIL), to represent predictive structures in machine learning.
  arXiv  Detail & Related papers  (2024-05-30T19:58:01Z)
• Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy [55.014926694758195]
  Entropy and mutual information in neural networks provide rich information on the learning process. We leverage data geometry to access the underlying manifold and reliably compute these information-theoretic measures. We show that they form noise-resistant measures of intrinsic dimensionality and relationship strength in high-dimensional simulated data.
  arXiv  Detail & Related papers  (2023-12-04T01:32:42Z)
• ARFA: An Asymmetric Receptive Field Autoencoder Model for Spatiotemporal Prediction [55.30913411696375]
  We propose an Asymmetric Receptive Field Autoencoder (ARFA) model, which introduces corresponding sizes of receptive field modules. In the encoder, we present large kernel module for globaltemporal feature extraction. In the decoder, we develop a small kernel module for localtemporal reconstruction. We construct the RainBench, a large-scale radar echo dataset for precipitation prediction, to address the scarcity of meteorological data in the domain.
  arXiv  Detail & Related papers  (2023-09-01T07:55:53Z)
• NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction [79.13750275141139]
  This paper proposes a novel and fast self-supervised solution for sparse-view CBCT reconstruction. The desired attenuation coefficients are represented as a continuous function of 3D spatial coordinates, parameterized by a fully-connected deep neural network. A learning-based encoder entailing hash coding is adopted to help the network capture high-frequency details.
  arXiv  Detail & Related papers  (2022-09-29T04:06:00Z)
• Toward a Geometrical Understanding of Self-supervised Contrastive Learning [55.83778629498769]
  Self-supervised learning (SSL) is one of the premier techniques to create data representations that are actionable for transfer learning in the absence of human annotations. Mainstream SSL techniques rely on a specific deep neural network architecture with two cascaded neural networks: the encoder and the projector. In this paper, we investigate how the strength of the data augmentation policies affects the data embedding.
  arXiv  Detail & Related papers  (2022-05-13T23:24:48Z)
• Neural RF SLAM for unsupervised positioning and mapping with channel state information [51.484516640867525]
  We present a neural network architecture for jointly learning user locations and environment mapping up to isometry. The proposed model learns an interpretable latent, i.e., user location, by just enforcing a physics-based decoder.
  arXiv  Detail & Related papers  (2022-03-15T21:32:44Z)
• Fractal Pyramid Networks [3.7384509727711923]
  We propose a new network architecture, the Fractal Pyramid Networks (PFNs) for pixel-wise prediction tasks. PFNs hold multiple information processing pathways and encode the information to multiple separate small-channel features. Our models can compete or outperform the state-of-the-art methods on the KITTI dataset with much fewer parameters.
  arXiv  Detail & Related papers  (2021-06-28T13:15:30Z)
• Neural Distributed Source Coding [59.630059301226474]
  We present a framework for lossy DSC that is agnostic to the correlation structure and can scale to high dimensions. We evaluate our method on multiple datasets and show that our method can handle complex correlations and state-of-the-art PSNR.
  arXiv  Detail & Related papers  (2021-06-05T04:50:43Z)
• Geometry-Aware Hamiltonian Variational Auto-Encoder [0.0]
  Variational auto-encoders (VAEs) have proven to be a well suited tool for performing dimensionality reduction by extracting latent variables lying in a potentially much smaller dimensional space than the data. However, such generative models may perform poorly when trained on small data sets which are abundant in many real-life fields such as medicine. We argue that such latent space modelling provides useful information about its underlying structure leading to far more meaningfuls, more realistic data-generation and more reliable clustering.
  arXiv  Detail & Related papers  (2020-10-22T08:26:46Z)

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.