Autoencoders
D Bank, N Koenigstein, R Giryes - … for data science handbook: data mining …, 2023 - Springer
An autoencoder is a specific type of a neural network, which is mainly designed to encode
the input into a compressed and meaningful representation and then decode it back such …
the input into a compressed and meaningful representation and then decode it back such …
[HTML][HTML] A survey on deep learning applied to medical images: from simple artificial neural networks to generative models
P Celard, EL Iglesias, JM Sorribes-Fdez… - Neural Computing and …, 2023 - Springer
Deep learning techniques, in particular generative models, have taken on great importance
in medical image analysis. This paper surveys fundamental deep learning concepts related …
in medical image analysis. This paper surveys fundamental deep learning concepts related …
Variational inference of disentangled latent concepts from unlabeled observations
Disentangled representations, where the higher level data generative factors are reflected in
disjoint latent dimensions, offer several benefits such as ease of deriving invariant …
disjoint latent dimensions, offer several benefits such as ease of deriving invariant …
Deep incomplete multi-view clustering with cross-view partial sample and prototype alignment
The success of existing multi-view clustering relies on the assumption of sample integrity
across multiple views. However, in real-world scenarios, samples of multi-view are partially …
across multiple views. However, in real-world scenarios, samples of multi-view are partially …
Deep appearance models for face rendering
We introduce a deep appearance model for rendering the human face. Inspired by Active
Appearance Models, we develop a data-driven rendering pipeline that learns a joint …
Appearance Models, we develop a data-driven rendering pipeline that learns a joint …
CyCU-Net: Cycle-consistency unmixing network by learning cascaded autoencoders
In recent years, deep learning (DL) has attracted increasing attention in hyperspectral
unmixing (HU) applications due to its powerful learning and data fitting ability. The …
unmixing (HU) applications due to its powerful learning and data fitting ability. The …
Shape-based generative modeling for de novo drug design
In this work, we propose a machine learning approach to generate novel molecules starting
from a seed compound, its three-dimensional (3D) shape, and its pharmacophoric features …
from a seed compound, its three-dimensional (3D) shape, and its pharmacophoric features …
Semi-supervised anomaly detection algorithms: A comparative summary and future research directions
ME Villa-Pérez, MA Alvarez-Carmona… - Knowledge-Based …, 2021 - Elsevier
While anomaly detection is relatively well-studied, it remains a topic of ongoing interest and
challenge, as our society becomes increasingly interconnected and digitalized. In this paper …
challenge, as our society becomes increasingly interconnected and digitalized. In this paper …
Deep learning in image cytometry: a review
Artificial intelligence, deep convolutional neural networks, and deep learning are all niche
terms that are increasingly appearing in scientific presentations as well as in the general …
terms that are increasingly appearing in scientific presentations as well as in the general …
On gans and gmms
E Richardson, Y Weiss - Advances in neural information …, 2018 - proceedings.neurips.cc
A longstanding problem in machine learning is to find unsupervised methods that can learn
the statistical structure of high dimensional signals. In recent years, GANs have gained much …
the statistical structure of high dimensional signals. In recent years, GANs have gained much …