Aaron Courville

Research interests

Publications

• Generative adversarial networks

  Communications of the ACM · 2020 · https://doi.org/10.1145/3422622

• MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis

  arXiv (Cornell University) · 2019 · https://doi.org/10.48550/arxiv.1910.06711

• FiLM: Visual Reasoning with a General Conditioning Layer

  Proceedings of the AAAI Conference on Artificial Intelligence · 2018 · https://doi.org/10.1609/aaai.v32i1.11671

• Mutual Information Neural Estimation.

  International Conference on Machine Learning · 2018

• A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues

  AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · 2017 · https://doi.org/10.1609/aaai.v31i1.10983

• A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images

  Journal of Healthcare Engineering · 2017 · https://doi.org/10.1155/2017/4037190

• A closer look at memorization in deep networks

  Jagiellonian University Repository (Jagiellonian University) · 2017

• Improved Training of Wasserstein GANs

  arXiv (Cornell University) · 2017 · https://doi.org/10.48550/arxiv.1704.00028

• Adversarially Learned Inference

  arXiv (Cornell University) · 2016 · https://doi.org/10.48550/arxiv.1606.00704

• Deep Learning

  Journal · 2016

• Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models

  AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · 2016 · https://doi.org/10.1609/aaai.v30i1.9883

• Brain tumor segmentation with Deep Neural Networks

  Medical Image Analysis · 2016 · https://doi.org/10.1016/j.media.2016.05.004

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

  arXiv (Cornell University) · 2015 · https://doi.org/10.48550/arxiv.1502.03044

• Show, Attend and Tell: Neural Image Caption Generation with Visual\n Attention

  arXiv (Cornell University) · 2015 · https://doi.org/10.48550/arxiv.1502.03044

• Describing Videos by Exploiting Temporal Structure

  Journal · 2015 · https://doi.org/10.1109/iccv.2015.512

• A Recurrent Latent Variable Model for Sequential Data

  arXiv (Cornell University) · 2015 · https://doi.org/10.48550/arxiv.1506.02216

• Challenges in representation learning: A report on three machine learning contests

  Neural Networks · 2014 · https://doi.org/10.1016/j.neunet.2014.09.005

• An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks

  arXiv (Cornell University) · 2014

• Generative Adversarial Networks

  arXiv (Cornell University) · 2014 · https://doi.org/10.48550/arxiv.1406.2661

• Representation Learning: A Review and New Perspectives

  IEEE Transactions on Pattern Analysis and Machine Intelligence · 2013 · https://doi.org/10.1109/tpami.2013.50

• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

  arXiv (Cornell University) · 2013 · https://doi.org/10.48550/arxiv.1308.3432

• Challenges in Representation Learning: A Report on Three Machine Learning Contests

  Lecture notes in computer science · 2013 · https://doi.org/10.1007/978-3-642-42051-1_16

• An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks

  arXiv (Cornell University) · 2013 · https://doi.org/10.48550/arxiv.1312.6211

• Why Does Unsupervised Pre-training Help Deep Learning?

  Journal · 2010

• An empirical evaluation of deep architectures on problems with many factors of variation

  Journal · 2007 · https://doi.org/10.1145/1273496.1273556

Current projects

No projects listed.