The Variational InfoMax AutoEncoder

2019-05-25 · Vincenzo Crescimanna, Bruce Graham

The Variational AutoEncoder (VAE) learns simultaneously an inference and a generative model, but only one of these models can be learned at optimum, this behaviour is associated to the ELBO learning objective, that is optimised by a non-informative generator. In order to solve such an issue, we provide a learning objective, learning a maximal informative generator while maintaining bounded the network capacity: the Variational InfoMax (VIM). The contribution of the VIM derivation is twofold: an objective learning both an optimal inference and generative model and the explicit definition of the network capacity, an estimation of the network robustness.

📄 PDF Abstract BibTeX arXiv:1905.10549

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Learning Representations by Maximizing Mutual Information in Variational Autoencoders

2019-12-21 · Ali Lotfi Rezaabad, Sriram Vishwanath

Variational autoencoders (VAEs) have ushered in a new era of unsupervised learning methods for complex distributions. Although these techniques are elegant in their approach, they are typically not useful for representat…

Representation Learning

An information theoretic approach to the autoencoder

2019-01-23 · Vincenzo Crescimanna, Bruce Graham

We present a variation of the Autoencoder (AE) that explicitly maximizes the mutual information between the input data and the hidden representation. The proposed model, the InfoMax Autoencoder (IMAE), by construction is…

Denoising

The Variational InfoMax Learning Objective

2020-03-07 · Vincenzo Crescimanna, Bruce Graham

Bayesian Inference and Information Bottleneck are the two most popular objectives for neural networks, but they can be optimised only via a variational lower bound: the Variational Information Bottleneck (VIB). In this m…

Bayesian Inference

Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction

2020-07-29 · Masashi Okada, Tadahiro Taniguchi

In the present paper, we propose a decoder-free extension of Dreamer, a leading model-based reinforcement learning (MBRL) method from pixels. Dreamer is a sample- and cost-efficient solution to robot learning, as it is u…

Contrastive Learning Data Augmentation Decoder Model-based Reinforcement Learning+4

Variational Autoencoders for Feature Detection of Magnetic Resonance Imaging Data

2016-03-21 · R. Devon Hjelm, Sergey M. Plis, Vince C. Calhoun

Independent component analysis (ICA), as an approach to the blind source-separation (BSS) problem, has become the de-facto standard in many medical imaging settings. Despite successes and a large ongoing research effort,…

blind source separation Dimensionality Reduction