Nonparametric guidance of autoencoder representations using label information

By Jasper Snoek, Ryan P. Adams, Hugo Larochelle. 2012

66 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Deeply-Supervised Nets (2014, background): “There are a few other relevant examples: in [24], label information is used for unsupervised learning, while in [28] semi-supervised learning is carried out in the context deep learning.”
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules (2016, background): “[40] The results reported in this work, and its application with carefully composed objective functions have the potential to create new avenues for molecular design.”
Manifold Gaussian Processes for regression (2014, positive): “In (Snoek et al., 2012), the objective for the optimization of the input transformation combines both an unsupervised and a supervised learning objective in a classiﬁcation context.”
Variational Auto-encoded Deep Gaussian Processes (2015, methodology): “In this section we consider two supervised learning problem instances: regression and Bayesian optimization (BO) (Osborne, 2010; Snoek et al., 2012b).”
Adaptive dropout for training deep neural networks (2013, methodology): “We formulate the data vector following Snoek et al.[17] by down-sampling from 96 × 96 to 32 × 32, so that the final training data vector has 2048 dimensions.”
A Review of Deep Learning Models for Time Series Prediction (2019, background): “…decoder, along with b and b as respective bias vectors. σ f and σ g denote the activation functions, which can be sigmoid, logistic, etc. [108], [109] Obviously, the parameters can be determined by minimizing reconstruction error E ( x , r ) , which is usually carried out by stochastic gradient…”
Deep Autoencoder based Energy Method for the Bending, Vibration, and Buckling Analysis of Kirchhoff Plates (2020, background): “It has also been proven to be an eﬀective way to learn and describe latent codes that reﬂect meaningful variations in data with an encoding and decoding layer [45].”