Advances in Neural Information Processing Systems 27

By Luigi Acerbi, Wei Ji Ma, Sethu Vijayakumar. 2014

153 citations recorded by the source corpus.

How researchers see this paper

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

1. Yoshua Bengio
2. Kyunghyun Cho
3. Quoc V. Le
4. Ruslan Salakhutdinov
5. Dong Yu
6. Sergey Levine
7. Zhe Gan
8. Li Deng

Citations in the corpus

• Conditional deep surrogate models for stochastic, high-dimensional, and multi-fidelity systems (2019, background): “0 our model has a direct correspondence with generative adversarial networks [53,54], while for λ > 1.”
• Rotation-invariant convolutional neural networks for galaxy morphology prediction (2015, background): “Gens & Domingos (2014) propose deep symmetry networks, a generalization of convolutional neural networks with the ability to form feature maps over any symmetry group, rather than just the translation group.”
• Invariant Representations for Noisy Speech Recognition (2016, methodology): “It is related to the idea of generative adversarial networks (GAN) and the gradient reverse method proposed in Goodfellow et al. (2014) and Ganin & Lempitsky (2014) respectively (Section 2).”
• Principal Component Analysis (2018, methodology): “Some of the studies that applied PCA are the classification of hyper-spectral data [129], face recognition [130], and to extract features from videos [131].”
• Score-based diffusion models for accelerated MRI (2021, methodology): “Score-based diffusion models are now one of the most popular methods in the context of image synthesis, matching the image fidelity of state-of-the-art GANs (Dhariwal and Nichol, 2021), and achieving the state-of-the-art log-likelihood on various datasets (Kingma et al., 2021; Kim et al., 2021).”
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables (2016, methodology): “To motivate the construction of Concrete random variables, we review a method for sampling from discrete distributions called the Gumbel-Max trick (Luce, 1959; Yellott, 1977; Papandreou & Yuille, 2011; Hazan & Jaakkola, 2012; Maddison et al., 2014).”
• Reconstruction of three-dimensional porous media using generative adversarial neural networks (2017, methodology): “as a methodology to learn a representation of a high-dimensional probability distribution from a given data set [31].”