Dumitru Erhan
Dumitru Erhan
Staff Research Scientist, Google Brain
Verifierad e-postadress på google.com - Startsida
Titel
Citeras av
Citeras av
År
Going deeper with convolutions
C Szegedy, W Liu, Y Jia, P Sermanet, S Reed, D Anguelov, D Erhan, ...
Proceedings of the IEEE conference on computer vision and pattern …, 2015
302032015
Ssd: Single shot multibox detector
W Liu, D Anguelov, D Erhan, C Szegedy, S Reed, CY Fu, AC Berg
European conference on computer vision, 21-37, 2016
142412016
Intriguing properties of neural networks
C Szegedy, W Zaremba, I Sutskever, J Bruna, D Erhan, I Goodfellow, ...
arXiv preprint arXiv:1312.6199, 2013
68812013
Show and tell: A neural image caption generator
O Vinyals, A Toshev, S Bengio, D Erhan
Proceedings of the IEEE conference on computer vision and pattern …, 2015
45902015
Why does unsupervised pre-training help deep learning?
D Erhan, A Courville, Y Bengio, P Vincent
Proceedings of the thirteenth international conference on artificial …, 2010
25472010
Deep neural networks for object detection
C Szegedy, A Toshev, D Erhan
12842013
Scalable object detection using deep neural networks
D Erhan, C Szegedy, A Toshev, D Anguelov
Proceedings of the IEEE conference on computer vision and pattern …, 2014
10552014
Unsupervised pixel-level domain adaptation with generative adversarial networks
K Bousmalis, N Silberman, D Dohan, D Erhan, D Krishnan
Proceedings of the IEEE conference on computer vision and pattern …, 2017
10432017
An empirical evaluation of deep architectures on problems with many factors of variation
H Larochelle, D Erhan, A Courville, J Bergstra, Y Bengio
Proceedings of the 24th international conference on Machine learning, 473-480, 2007
10362007
Visualizing higher-layer features of a deep network
D Erhan, Y Bengio, A Courville, P Vincent
University of Montreal 1341 (3), 1, 2009
9832009
Domain separation networks
K Bousmalis, G Trigeorgis, N Silberman, D Krishnan, D Erhan
arXiv preprint arXiv:1608.06019, 2016
8122016
Theano: A Python framework for fast computation of mathematical expressions
R Al-Rfou, G Alain, A Almahairi, C Angermueller, D Bahdanau, N Ballas, ...
arXiv e-prints, arXiv: 1605.02688, 2016
773*2016
Challenges in representation learning: A report on three machine learning contests
IJ Goodfellow, D Erhan, PL Carrier, A Courville, M Mirza, B Hamner, ...
International conference on neural information processing, 117-124, 2013
7232013
Show and tell: Lessons learned from the 2015 mscoco image captioning challenge
O Vinyals, A Toshev, S Bengio, D Erhan
IEEE transactions on pattern analysis and machine intelligence 39 (4), 652-663, 2016
6092016
Training deep neural networks on noisy labels with bootstrapping
S Reed, H Lee, D Anguelov, C Szegedy, D Erhan, A Rabinovich
arXiv preprint arXiv:1412.6596, 2014
5312014
The difficulty of training deep architectures and the effect of unsupervised pre-training
D Erhan, PA Manzagol, Y Bengio, S Bengio, P Vincent
Artificial Intelligence and Statistics, 153-160, 2009
4742009
Scalable, high-quality object detection
C Szegedy, S Reed, D Erhan, D Anguelov, S Ioffe
arXiv preprint arXiv:1412.1441, 2014
3942014
Aggregate features and ADABOOST for music classification
J Bergstra, N Casagrande, D Erhan, D Eck, B Kégl
Machine learning 65 (2-3), 473-484, 2006
3602006
Zero-data learning of new tasks.
H Larochelle, D Erhan, Y Bengio
AAAI 1 (2), 3, 2008
3332008
Stochastic variational video prediction
M Babaeizadeh, C Finn, D Erhan, RH Campbell, S Levine
arXiv preprint arXiv:1710.11252, 2017
2692017
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–20