Reducing the Dimensionality of Data with Neural

By Geoffrey E. Hinton. 2008

2,474 citations recorded by the source corpus.

Subfields: 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 Representation & Self-Supervised Learning

Citations in the corpus

Adam: A Method for Stochastic Optimization (2014, methodology): “SGD proved itself as an efﬁcient and effective optimization method that was central in many machine learning success stories, such as recent advances in deep learning (Deng et al., 2013; Krizhevsky et al., 2012; Hinton & Salakhutdinov, 2006; Hinton et al., 2012a; Graves et al., 2013).”
Generating Images with Perceptual Similarity Metrics based on Deep Networks (2016, methodology): “Au-toencoders (Hinton & Salakhutdinov, 2006; Vincent et al., 2008) have been widely used for unsupervised learning and generative modeling, too.”
Learning Adversarially Fair and Transferable Representations (2018, methodology): “The others all involved learning separate representations on the original task, and freezing the encoder as previously described; the internal representations of MLPs have been shown to contain useful information (Hinton & Salakhutdinov, 2006).”
Krylov Subspace Descent for Deep Learning (2011, methodology): “For MNISTCL,PT we initialize the weights using pretraining RBMs as in [5].”
DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection (2014, background): “Deep models have achieved spectacular progress in computer vision [26, 27, 43, 28, 30, 37, 29, 63, 33, 50, 18, 42].”
Pre-trained models for natural language processing: A survey (2020, background): “As early as 2006, the breakthrough of deep learning came with greedy layer-wise unsupervised pre-training followed by supervised fine-tuning [28].”
Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks (2017, background): “, Yang Qiang <yangqiang@mail.bafst.com>. pre-training (Hinton et al., 2006; Hinton & Salakhutdinov, 2006), special network structure (Simonyan & Zisserman, 2014; Szegedy et al., 2015; He et al., 2016), ReLU activation (Nair & Hinton, 2010; Maas et al., 2013), noise injecting (Wan et al., 2013;…”