R
Ricky T. Q. Chen
Researcher at University of Toronto
Publications - 43
Citations - 4936
Ricky T. Q. Chen is an academic researcher from University of Toronto. The author has contributed to research in topics: Computer science & Ode. The author has an hindex of 14, co-authored 30 publications receiving 4091 citations.
Papers
More filters
Proceedings Article
Neural ordinary differential equations
TL;DR: In this paper, the authors introduce a new family of deep neural network models called continuous normalizing flows, which parameterize the derivative of the hidden state using a neural network, and the output of the network is computed using a black-box differential equation solver.
Posted Content
Neural Ordinary Differential Equations
TL;DR: In this paper, the authors introduce a new family of deep neural network models called continuous normalizing flows, which parameterize the derivative of the hidden state using a neural network, and the output of the network is computed using a black-box differential equation solver.
Posted Content
Isolating Sources of Disentanglement in Variational Autoencoders
TL;DR: In this article, the authors decompose the evidence lower bound to show the existence of a term measuring the total correlation between latent variables and use this to motivate the Total Correlation Variational Autoencoder (TCVAE), a refinement of the state-of-the-art VAE objective for learning disentangled representations.
Proceedings Article
FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
TL;DR: This paper uses Hutchinson's trace estimator to give a scalable unbiased estimate of the log-density and demonstrates the approach on high-dimensional density estimation, image generation, and variational inference, achieving the state-of-the-art among exact likelihood methods with efficient sampling.
Posted Content
Invertible Residual Networks
TL;DR: Invertible ResNets as mentioned in this paper make the same ResNet architectures invertible, allowing the same model to be used for classification, density estimation, and generation, without partitioning dimensions or restricting network architectures.