Probabilistic Autoencoder using Fisher Information
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Uncertainty-Masked Bernoulli Diffusion for Camouflaged Object Detection Refinement
Probabilistic Variational Contrastive Learning
Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents
Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression
Statistical Machine Learning for Astronomy -- A Textbook
Making Language Model a Hierarchical Classifier and Generator
토론
이 논문과 연결된 포럼 글이 아직 없습니다.