| Generating images with recurrent adversarial networks DJ Im, CD Kim, H Jiang, R Memisevic arXiv preprint arXiv:1602.05110, 2016 | 167 | 2016 |
| Denoising criterion for variational auto-encoding framework DIJ Im, S Ahn, R Memisevic, Y Bengio Thirty-First AAAI Conference on Artificial Intelligence, 2017 | 75 | 2017 |
| Quantitatively evaluating GANs with divergences proposed for training DJ Im, H Ma, G Taylor, K Branson arXiv preprint arXiv:1803.01045, 2018 | 41 | 2018 |
| An empirical analysis of deep network loss surfaces DJ Im, M Tao, K Branson | 27 | 2016 |
| Neural machine translation with gumbel-greedy decoding J Gu, DJ Im, VOK Li Thirty-Second AAAI Conference on Artificial Intelligence, 2018 | 23 | 2018 |
| Generative adversarial parallelization DJ Im, H Ma, CD Kim, G Taylor arXiv preprint arXiv:1612.04021, 2016 | 17 | 2016 |
| Semisupervised hyperspectral image classification via neighborhood graph learning DJ Im, GW Taylor IEEE Geoscience and Remote Sensing Letters 12 (9), 1913-1917, 2015 | 12 | 2015 |
| An empirical analysis of the optimization of deep network loss surfaces DJ Im, M Tao, K Branson arXiv preprint arXiv:1612.04010, 2016 | 11 | 2016 |
| Conservativeness of untied auto-encoders DJ Im, MI Belghazi, R Memisevic Thirtieth AAAI Conference on Artificial Intelligence, 2016 | 7 | 2016 |
| Neural network regularization via robust weight factorization J Rudy, W Ding, DJ Im, GW Taylor arXiv preprint arXiv:1412.6630, 2014 | 6 | 2014 |
| Generative adversarial metric DJ Im, CD Kim, H Jiang, R Memisevic | 5 | 2016 |
| Learning a metric for class-conditional KNN DJ Im, GW Taylor 2016 International Joint Conference on Neural Networks (IJCNN), 1932-1939, 2016 | 3 | 2016 |
| Stochastic Neighbor Embedding under f-divergences DJ Im, N Verma, K Branson arXiv preprint arXiv:1811.01247, 2018 | 2 | 2018 |
| Importance Weighted Adversarial Variational Autoencoders for Spike Inference from Calcium Imaging Data DJ Im, S Prakhya, J Yan, S Turaga, K Branson arXiv preprint arXiv:1906.03214, 2019 | 1 | 2019 |
| Scoring and classifying with Gated auto-encoders DJ Im, GW Taylor Joint European Conference on Machine Learning and Knowledge Discovery in …, 2015 | 1 | 2015 |
| Understanding minimum probability flow for RBMs under various kinds of dynamics DJ Im, E Buchman, GW Taylor arXiv preprint arXiv:1412.6617, 2014 | 1 | 2014 |
| Are skip connections necessary for biologically plausible learning rules? DJ Im, R Patil, K Branson arXiv preprint arXiv:2001.01647, 2019 | | 2019 |
| Model-Agnostic Meta-Learning using Runge-Kutta Methods DJ Im, Y Jiang, N Verma arXiv preprint arXiv:1910.07368, 2019 | | 2019 |
| An empirical investigation of minimum probability flow learning under different connectivity patterns DJ Im, E Buchman, GW Taylor Joint European Conference on Machine Learning and Knowledge Discovery in …, 2015 | | 2015 |
| Analyzing Unsupervised Representation Learning Models Under the View of Dynamical Systems J Im | | 2015 |
Graham TaylorUniversity of Guelph and Vector Institute for Artificial IntelligenceVerified email at uoguelph.ca
