Results 251 to 260 of about 30,442 (292)

A deep ensemble encoder network method for improved polygenic risk score prediction. [PDF]

BioData Min
Ozdemir OB, Chen R, Wu O, Li R.
europepmc   +1 more source

Research on a lead-acid battery fault detection method based on LSTM-AE-Cosine. [PDF]

PLoS One
Liu L, Xu H, Tang H, Cui J, Feng L, Deng K.   +5 more
europepmc   +1 more source

Attention-driven fusion of sequential and graph neural models for insider threat detection in UEBA. [PDF]

Sci Rep
Paduvilan AK, Babu SA, Sekar J, Elengovan AK, Seshagiri N, Jangiti K, Selvam AK.   +6 more
europepmc   +1 more source

Learning the reaction coordinate: collective variables from physical intuition to generative models.

Digit Discov
Talmazan RA, Chen CG, Tang C, Megías A, Contreras Arredondo S, Chipot C.   +5 more
europepmc   +1 more source

Steering generative models for protein design: Aligning and conditioning strategies.

Curr Opin Struct Biol
Stocco F, Garibbo M, Ferruz N.
europepmc   +1 more source

Information Flows of Diverse Autoencoders

Entropy, 2021
Deep learning methods have had outstanding performances in various fields. A fundamental query is why they are so effective. Information theory provides a potential answer by interpreting the learning process as the information transmission and ...
Sungyeop Lee, Junghyo Jo
exaly   +2 more sources

Some of the next articles are maybe not open access.

Related searches:

AE2-Nets: Autoencoder in Autoencoder Networks

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Learning on data represented with multiple views (e.g., multiple types of descriptors or modalities) is a rapidly growing direction in machine learning and computer vision. Although effectiveness achieved, most existing algorithms usually focus on classification or clustering tasks.
Changqing Zhang 0002, Yeqing Liu, Huazhu Fu   +2 more
openaire   +2 more sources

AutoEncoder for Neuroimage

2021
Variational AutoEncoder (VAE) as a class of neural networks performing nonlinear dimensionality reduction has become an effective tool in neuroimaging analysis. Currently, most studies on VAE consider unsupervised learning to capture the latent representations and to some extent, this strategy may be under-explored in the case of heavy noise and ...
Mingli Zhang, Fan Zhang 0045, Jianxin Zhang 0001, Ahmad Chaddad, Fenghua Guo, Wenbin Zhang 0002, Ji Zhang 0001, Alan C. Evans   +7 more
openaire   +2 more sources

Retinex by Autoencoders

2022 16th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), 2022
The Retinex algorithms find wide applications as image enhancers, for their capability of preserving edges, while at the same time attenuating smooth gradients and chromatic dominants. They are characterized by the fact that the output chromatic intensity of a pixel is not determined in isolation (or looking only at the contiguous pixels) but through ...
Pezzoni, Claudio, Mio, Corrado, Barsotti, Annalisa, Gianini, Gabriele   +3 more
openaire   +3 more sources