forked from terryum/awesome-deep-learning-papers
-
Notifications
You must be signed in to change notification settings - Fork 1
/
top100papers.bib
730 lines (728 loc) · 29.6 KB
/
top100papers.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
@article{hinton2015distilling,
title={Distilling the knowledge in a neural network},
author={Hinton, Geoffrey and Vinyals, Oriol and Dean, Jeff},
journal={arXiv preprint arXiv:1503.02531},
year={2015}
}
@inproceedings{nguyen2015deep,
title={Deep neural networks are easily fooled: High confidence predictions for unrecognizable images},
author={Nguyen, Anh and Yosinski, Jason and Clune, Jeff},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={427--436},
year={2015}
}
@inproceedings{yosinski2014transferable,
title={How transferable are features in deep neural networks?},
author={Yosinski, Jason and Clune, Jeff and Bengio, Yoshua and Lipson, Hod},
booktitle={Advances in neural information processing systems},
pages={3320--3328},
year={2014}
}
@inproceedings{sharif2014cnn,
title={CNN features off-the-shelf: an astounding baseline for recognition},
author={Sharif Razavian, Ali and Azizpour, Hossein and Sullivan, Josephine and Carlsson, Stefan},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops},
pages={806--813},
year={2014}
}
@inproceedings{oquab2014learning,
title={Learning and transferring mid-level image representations using convolutional neural networks},
author={Oquab, Maxime and Bottou, Leon and Laptev, Ivan and Sivic, Josef},
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
pages={1717--1724},
year={2014}
}
@inproceedings{zeiler2014visualizing,
title={Visualizing and understanding convolutional networks},
author={Zeiler, Matthew D and Fergus, Rob},
booktitle={European conference on computer vision},
pages={818--833},
year={2014},
organization={Springer}
}
@inproceedings{donahue2014decaf,
title={DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition.},
author={Donahue, Jeff and Jia, Yangqing and Vinyals, Oriol and Hoffman, Judy and Zhang, Ning and Tzeng, Eric and Darrell, Trevor},
booktitle={Icml},
volume={32},
pages={647--655},
year={2014}
}
@inproceedings{srivastava2015training,
title={Training very deep networks},
author={Srivastava, Rupesh K and Greff, Klaus and Schmidhuber, J{\"u}rgen},
booktitle={Advances in neural information processing systems},
pages={2377--2385},
year={2015}
}
@article{ioffe2015batch,
title={Batch normalization: Accelerating deep network training by reducing internal covariate shift},
author={Ioffe, Sergey and Szegedy, Christian},
journal={arXiv preprint arXiv:1502.03167},
year={2015}
}
@inproceedings{he2015delving,
title={Delving deep into rectifiers: Surpassing human-level performance on imagenet classification},
author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
booktitle={Proceedings of the IEEE international conference on computer vision},
pages={1026--1034},
year={2015}
}
@article{srivastava2014dropout,
title={Dropout: a simple way to prevent neural networks from overfitting.},
author={Srivastava, Nitish and Hinton, Geoffrey E and Krizhevsky, Alex and Sutskever, Ilya and Salakhutdinov, Ruslan},
journal={Journal of Machine Learning Research},
volume={15},
number={1},
pages={1929--1958},
year={2014}
}
@article{kingma2014adam,
title={Adam: A method for stochastic optimization},
author={Kingma, Diederik and Ba, Jimmy},
journal={arXiv preprint arXiv:1412.6980},
year={2014}
}
@article{hinton2012improving,
title={Improving neural networks by preventing co-adaptation of feature detectors},
author={Hinton, Geoffrey E and Srivastava, Nitish and Krizhevsky, Alex and Sutskever, Ilya and Salakhutdinov, Ruslan R},
journal={arXiv preprint arXiv:1207.0580},
year={2012}
}
@article{bergstra2012random,
title={Random search for hyper-parameter optimization},
author={Bergstra, James and Bengio, Yoshua},
journal={Journal of Machine Learning Research},
volume={13},
number={Feb},
pages={281--305},
year={2012}
}
@article{oord2016pixel,
title={Pixel recurrent neural networks},
author={Oord, Aaron van den and Kalchbrenner, Nal and Kavukcuoglu, Koray},
journal={arXiv preprint arXiv:1601.06759},
year={2016}
}
@inproceedings{salimans2016improved,
title={Improved techniques for training gans},
author={Salimans, Tim and Goodfellow, Ian and Zaremba, Wojciech and Cheung, Vicki and Radford, Alec and Chen, Xi},
booktitle={Advances in Neural Information Processing Systems},
pages={2226--2234},
year={2016}
}
@article{radford2015unsupervised,
title={Unsupervised representation learning with deep convolutional generative adversarial networks},
author={Radford, Alec and Metz, Luke and Chintala, Soumith},
journal={arXiv preprint arXiv:1511.06434},
year={2015}
}
@article{gregor2015draw,
title={DRAW: A recurrent neural network for image generation},
author={Gregor, Karol and Danihelka, Ivo and Graves, Alex and Rezende, Danilo Jimenez and Wierstra, Daan},
journal={arXiv preprint arXiv:1502.04623},
year={2015}
}
@inproceedings{goodfellow2014generative,
title={Generative adversarial nets},
author={Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua},
booktitle={Advances in neural information processing systems},
pages={2672--2680},
year={2014}
}
@article{kingma2013auto,
title={Auto-encoding variational bayes},
author={Kingma, Diederik P and Welling, Max},
journal={arXiv preprint arXiv:1312.6114},
year={2013}
}
@inproceedings{le2013building,
title={Building high-level features using large scale unsupervised learning},
author={Le, Quoc V},
booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on},
pages={8595--8598},
year={2013},
organization={IEEE}
}
@inproceedings{szegedy2016rethinking,
title={Rethinking the inception architecture for computer vision},
author={Szegedy, Christian and Vanhoucke, Vincent and Ioffe, Sergey and Shlens, Jon and Wojna, Zbigniew},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={2818--2826},
year={2016}
}
@article{szegedy2016inception,
title={Inception-v4, inception-resnet and the impact of residual connections on learning},
author={Szegedy, Christian and Ioffe, Sergey and Vanhoucke, Vincent and Alemi, Alex},
journal={arXiv preprint arXiv:1602.07261},
year={2016}
}
@inproceedings{he2016identity,
title={Identity mappings in deep residual networks},
author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
booktitle={European Conference on Computer Vision},
pages={630--645},
year={2016},
organization={Springer}
}
@inproceedings{he2016deep,
title={Deep residual learning for image recognition},
author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={770--778},
year={2016}
}
@inproceedings{szegedy2015going,
title={Going deeper with convolutions},
author={Szegedy, Christian and Liu, Wei and Jia, Yangqing and Sermanet, Pierre and Reed, Scott and Anguelov, Dragomir and Erhan, Dumitru and Vanhoucke, Vincent and Rabinovich, Andrew},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={1--9},
year={2015}
}
@article{simonyan2014very,
title={Very deep convolutional networks for large-scale image recognition},
author={Simonyan, Karen and Zisserman, Andrew},
journal={arXiv preprint arXiv:1409.1556},
year={2014}
}
@inproceedings{he2014spatial,
title={Spatial pyramid pooling in deep convolutional networks for visual recognition},
author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
booktitle={European Conference on Computer Vision},
pages={346--361},
year={2014},
organization={Springer}
}
@article{chatfield2014return,
title={Return of the devil in the details: Delving deep into convolutional nets},
author={Chatfield, Ken and Simonyan, Karen and Vedaldi, Andrea and Zisserman, Andrew},
journal={arXiv preprint arXiv:1405.3531},
year={2014}
}
@article{sermanet2013overfeat,
title={Overfeat: Integrated recognition, localization and detection using convolutional networks},
author={Sermanet, Pierre and Eigen, David and Zhang, Xiang and Mathieu, Micha{\"e}l and Fergus, Rob and LeCun, Yann},
journal={arXiv preprint arXiv:1312.6229},
year={2013}
}
@article{goodfellow2013maxout,
title={Maxout Networks.},
author={Goodfellow, Ian J and Warde-Farley, David and Mirza, Mehdi and Courville, Aaron C and Bengio, Yoshua},
journal={ICML (3)},
volume={28},
pages={1319--1327},
year={2013}
}
@article{lin2013network,
title={Network in network},
author={Lin, Min and Chen, Qiang and Yan, Shuicheng},
journal={arXiv preprint arXiv:1312.4400},
year={2013}
}
@inproceedings{krizhevsky2012imagenet,
title={Imagenet classification with deep convolutional neural networks},
author={Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E},
booktitle={Advances in neural information processing systems},
pages={1097--1105},
year={2012}
}
@inproceedings{redmon2016you,
title={You only look once: Unified, real-time object detection},
author={Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={779--788},
year={2016}
}
@article{girshick2016region,
title={Region-based convolutional networks for accurate object detection and segmentation},
author={Girshick, Ross and Donahue, Jeff and Darrell, Trevor and Malik, Jitendra},
journal={IEEE transactions on pattern analysis and machine intelligence},
volume={38},
number={1},
pages={142--158},
year={2016},
publisher={IEEE}
}
@inproceedings{long2015fully,
title={Fully convolutional networks for semantic segmentation},
author={Long, Jonathan and Shelhamer, Evan and Darrell, Trevor},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={3431--3440},
year={2015}
}
@inproceedings{ren2015faster,
title={Faster r-cnn: Towards real-time object detection with region proposal networks},
author={Ren, Shaoqing and He, Kaiming and Girshick, Ross and Sun, Jian},
booktitle={Advances in neural information processing systems},
pages={91--99},
year={2015}
}
@inproceedings{girshick2015fast,
title={Fast r-cnn},
author={Girshick, Ross},
booktitle={Proceedings of the IEEE International Conference on Computer Vision},
pages={1440--1448},
year={2015}
}
@inproceedings{girshick2014rich,
title={Rich feature hierarchies for accurate object detection and semantic segmentation},
author={Girshick, Ross and Donahue, Jeff and Darrell, Trevor and Malik, Jitendra},
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
pages={580--587},
year={2014}
}
@article{chen2014semantic,
title={Semantic image segmentation with deep convolutional nets and fully connected crfs},
author={Chen, Liang-Chieh and Papandreou, George and Kokkinos, Iasonas and Murphy, Kevin and Yuille, Alan L},
journal={arXiv preprint arXiv:1412.7062},
year={2014}
}
@article{farabet2013learning,
title={Learning hierarchical features for scene labeling},
author={Farabet, Clement and Couprie, Camille and Najman, Laurent and LeCun, Yann},
journal={IEEE transactions on pattern analysis and machine intelligence},
volume={35},
number={8},
pages={1915--1929},
year={2013},
publisher={IEEE}
}
@article{dong2016image,
title={Image super-resolution using deep convolutional networks},
author={Dong, Chao and Loy, Chen Change and He, Kaiming and Tang, Xiaoou},
journal={IEEE transactions on pattern analysis and machine intelligence},
volume={38},
number={2},
pages={295--307},
year={2016},
publisher={IEEE}
}
@article{gatys2015neural,
title={A neural algorithm of artistic style},
author={Gatys, Leon A and Ecker, Alexander S and Bethge, Matthias},
journal={arXiv preprint arXiv:1508.06576},
year={2015}
}
@inproceedings{karpathy2015deep,
title={Deep visual-semantic alignments for generating image descriptions},
author={Karpathy, Andrej and Fei-Fei, Li},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={3128--3137},
year={2015}
}
@inproceedings{xu2015show,
title={Show, Attend and Tell: Neural Image Caption Generation with Visual Attention.},
author={Xu, Kelvin and Ba, Jimmy and Kiros, Ryan and Cho, Kyunghyun and Courville, Aaron C and Salakhutdinov, Ruslan and Zemel, Richard S and Bengio, Yoshua},
booktitle={ICML},
volume={14},
pages={77--81},
year={2015}
}
@inproceedings{vinyals2015show,
title={Show and tell: A neural image caption generator},
author={Vinyals, Oriol and Toshev, Alexander and Bengio, Samy and Erhan, Dumitru},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={3156--3164},
year={2015}
}
@inproceedings{donahue2015long,
title={Long-term recurrent convolutional networks for visual recognition and description},
author={Donahue, Jeffrey and Anne Hendricks, Lisa and Guadarrama, Sergio and Rohrbach, Marcus and Venugopalan, Subhashini and Saenko, Kate and Darrell, Trevor},
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
pages={2625--2634},
year={2015}
}
@inproceedings{antol2015vqa,
title={Vqa: Visual question answering},
author={Antol, Stanislaw and Agrawal, Aishwarya and Lu, Jiasen and Mitchell, Margaret and Batra, Dhruv and Lawrence Zitnick, C and Parikh, Devi},
booktitle={Proceedings of the IEEE International Conference on Computer Vision},
pages={2425--2433},
year={2015}
}
@inproceedings{taigman2014deepface,
title={Deepface: Closing the gap to human-level performance in face verification},
author={Taigman, Yaniv and Yang, Ming and Ranzato, Marc'Aurelio and Wolf, Lior},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={1701--1708},
year={2014}
}
@inproceedings{karpathy2014large,
title={Large-scale video classification with convolutional neural networks},
author={Karpathy, Andrej and Toderici, George and Shetty, Sanketh and Leung, Thomas and Sukthankar, Rahul and Fei-Fei, Li},
booktitle={Proceedings of the IEEE conference on Computer Vision and Pattern Recognition},
pages={1725--1732},
year={2014}
}
@inproceedings{toshev2014deeppose,
title={Deeppose: Human pose estimation via deep neural networks},
author={Toshev, Alexander and Szegedy, Christian},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={1653--1660},
year={2014}
}
@inproceedings{simonyan2014two,
title={Two-stream convolutional networks for action recognition in videos},
author={Simonyan, Karen and Zisserman, Andrew},
booktitle={Advances in neural information processing systems},
pages={568--576},
year={2014}
}
@article{ji20133d,
title={3D convolutional neural networks for human action recognition},
author={Ji, Shuiwang and Xu, Wei and Yang, Ming and Yu, Kai},
journal={IEEE transactions on pattern analysis and machine intelligence},
volume={35},
number={1},
pages={221--231},
year={2013},
publisher={IEEE}
}
@inproceedings{zheng2015conditional,
title={Conditional random fields as recurrent neural networks},
author={Zheng, Shuai and Jayasumana, Sadeep and Romera-Paredes, Bernardino and Vineet, Vibhav and Su, Zhizhong and Du, Dalong and Huang, Chang and Torr, Philip HS},
booktitle={Proceedings of the IEEE International Conference on Computer Vision},
pages={1529--1537},
year={2015}
}
@article{weston2014memory,
title={Memory networks},
author={Weston, Jason and Chopra, Sumit and Bordes, Antoine},
journal={arXiv preprint arXiv:1410.3916},
year={2014}
}
@article{graves2014neural,
title={Neural turing machines},
author={Graves, Alex and Wayne, Greg and Danihelka, Ivo},
journal={arXiv preprint arXiv:1410.5401},
year={2014}
}
@article{graves2013generating,
title={Generating sequences with recurrent neural networks},
author={Graves, Alex},
journal={arXiv preprint arXiv:1308.0850},
year={2013}
}
@article{chung2016character,
title={A character-level decoder without explicit segmentation for neural machine translation},
author={Chung, Junyoung and Cho, Kyunghyun and Bengio, Yoshua},
journal={arXiv preprint arXiv:1603.06147},
year={2016}
}
@article{jozefowicz2016exploring,
title={Exploring the limits of language modeling},
author={Jozefowicz, Rafal and Vinyals, Oriol and Schuster, Mike and Shazeer, Noam and Wu, Yonghui},
journal={arXiv preprint arXiv:1602.02410},
year={2016}
}
@inproceedings{hermann2015teaching,
title={Teaching machines to read and comprehend},
author={Hermann, Karl Moritz and Kocisky, Tomas and Grefenstette, Edward and Espeholt, Lasse and Kay, Will and Suleyman, Mustafa and Blunsom, Phil},
booktitle={Advances in Neural Information Processing Systems},
pages={1693--1701},
year={2015}
}
@article{luong2015effective,
title={Effective approaches to attention-based neural machine translation},
author={Luong, Minh-Thang and Pham, Hieu and Manning, Christopher D},
journal={arXiv preprint arXiv:1508.04025},
year={2015}
}
@article{bahdanau2014neural,
title={Neural machine translation by jointly learning to align and translate},
author={Bahdanau, Dzmitry and Cho, Kyunghyun and Bengio, Yoshua},
journal={arXiv preprint arXiv:1409.0473},
year={2014}
}
@inproceedings{sutskever2014sequence,
title={Sequence to sequence learning with neural networks},
author={Sutskever, Ilya and Vinyals, Oriol and Le, Quoc V},
booktitle={Advances in neural information processing systems},
pages={3104--3112},
year={2014}
}
@article{cho2014learning,
title={Learning phrase representations using RNN encoder-decoder for statistical machine translation},
author={Cho, Kyunghyun and Van Merri{\"e}nboer, Bart and Gulcehre, Caglar and Bahdanau, Dzmitry and Bougares, Fethi and Schwenk, Holger and Bengio, Yoshua},
journal={arXiv preprint arXiv:1406.1078},
year={2014}
}
@article{kalchbrenner2014convolutional,
title={A convolutional neural network for modelling sentences},
author={Kalchbrenner, Nal and Grefenstette, Edward and Blunsom, Phil},
journal={arXiv preprint arXiv:1404.2188},
year={2014}
}
@article{kim2014convolutional,
title={Convolutional neural networks for sentence classification},
author={Kim, Yoon},
journal={arXiv preprint arXiv:1408.5882},
year={2014}
}
@inproceedings{pennington2014glove,
title={Glove: Global Vectors for Word Representation.},
author={Pennington, Jeffrey and Socher, Richard and Manning, Christopher D},
booktitle={EMNLP},
volume={14},
pages={1532--1543},
year={2014}
}
@inproceedings{le2014distributed,
title={Distributed Representations of Sentences and Documents.},
author={Le, Quoc V and Mikolov, Tomas},
booktitle={ICML},
volume={14},
pages={1188--1196},
year={2014}
}
@inproceedings{mikolov2013distributed,
title={Distributed representations of words and phrases and their compositionality},
author={Mikolov, Tomas and Sutskever, Ilya and Chen, Kai and Corrado, Greg S and Dean, Jeff},
booktitle={Advances in neural information processing systems},
pages={3111--3119},
year={2013}
}
@article{mikolov2013efficient,
title={Efficient estimation of word representations in vector space},
author={Mikolov, Tomas and Chen, Kai and Corrado, Greg and Dean, Jeffrey},
journal={arXiv preprint arXiv:1301.3781},
year={2013}
}
@inproceedings{socher2013recursive,
title={Recursive deep models for semantic compositionality over a sentiment treebank},
author={Socher, Richard and Perelygin, Alex and Wu, Jean Y and Chuang, Jason and Manning, Christopher D and Ng, Andrew Y and Potts, Christopher and others},
booktitle={Proceedings of the conference on empirical methods in natural language processing (EMNLP)},
volume={1631},
pages={1642},
year={2013},
organization={Citeseer}
}
@inproceedings{bahdanau2016end,
title={End-to-end attention-based large vocabulary speech recognition},
author={Bahdanau, Dzmitry and Chorowski, Jan and Serdyuk, Dmitriy and Brakel, Philemon and Bengio, Yoshua},
booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on},
pages={4945--4949},
year={2016},
organization={IEEE}
}
@article{amodei2015deep,
title={Deep speech 2: End-to-end speech recognition in english and mandarin},
author={Amodei, Dario and Anubhai, Rishita and Battenberg, Eric and Case, Carl and Casper, Jared and Catanzaro, Bryan and Chen, Jingdong and Chrzanowski, Mike and Coates, Adam and Diamos, Greg and others},
journal={arXiv preprint arXiv:1512.02595},
year={2015}
}
@inproceedings{graves2013speech,
title={Speech recognition with deep recurrent neural networks},
author={Graves, Alex and Mohamed, Abdel-rahman and Hinton, Geoffrey},
booktitle={Acoustics, speech and signal processing (icassp), 2013 ieee international conference on},
pages={6645--6649},
year={2013},
organization={IEEE}
}
@article{hinton2012deep,
title={Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups},
author={Hinton, Geoffrey and Deng, Li and Yu, Dong and Dahl, George E and Mohamed, Abdel-rahman and Jaitly, Navdeep and Senior, Andrew and Vanhoucke, Vincent and Nguyen, Patrick and Sainath, Tara N and others},
journal={IEEE Signal Processing Magazine},
volume={29},
number={6},
pages={82--97},
year={2012},
publisher={IEEE}
}
@article{dahl2012context,
title={Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition},
author={Dahl, George E and Yu, Dong and Deng, Li and Acero, Alex},
journal={IEEE Transactions on Audio, Speech, and Language Processing},
volume={20},
number={1},
pages={30--42},
year={2012},
publisher={IEEE}
}
@article{mohamed2012acoustic,
title={Acoustic modeling using deep belief networks},
author={Mohamed, Abdel-rahman and Dahl, George E and Hinton, Geoffrey},
journal={IEEE Transactions on Audio, Speech, and Language Processing},
volume={20},
number={1},
pages={14--22},
year={2012},
publisher={IEEE}
}
@article{levine2016end,
title={End-to-end training of deep visuomotor policies},
author={Levine, Sergey and Finn, Chelsea and Darrell, Trevor and Abbeel, Pieter},
journal={Journal of Machine Learning Research},
volume={17},
number={39},
pages={1--40},
year={2016}
}
@article{levine2016learning,
title={Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection},
author={Levine, Sergey and Pastor, Peter and Krizhevsky, Alex and Quillen, Deirdre},
journal={arXiv preprint arXiv:1603.02199},
year={2016}
}
@inproceedings{mnih2016asynchronous,
title={Asynchronous methods for deep reinforcement learning},
author={Mnih, Volodymyr and Badia, Adria Puigdomenech and Mirza, Mehdi and Graves, Alex and Lillicrap, Timothy P and Harley, Tim and Silver, David and Kavukcuoglu, Koray},
booktitle={International Conference on Machine Learning},
year={2016}
}
@inproceedings{van2016deep,
title={Deep Reinforcement Learning with Double Q-Learning.},
author={Van Hasselt, Hado and Guez, Arthur and Silver, David},
booktitle={AAAI},
pages={2094--2100},
year={2016}
}
@article{silver2016mastering,
title={Mastering the game of Go with deep neural networks and tree search},
author={Silver, David and Huang, Aja and Maddison, Chris J and Guez, Arthur and Sifre, Laurent and Van Den Driessche, George and Schrittwieser, Julian and Antonoglou, Ioannis and Panneershelvam, Veda and Lanctot, Marc and others},
journal={Nature},
volume={529},
number={7587},
pages={484--489},
year={2016},
publisher={Nature Publishing Group}
}
@article{lillicrap2015continuous,
title={Continuous control with deep reinforcement learning},
author={Lillicrap, Timothy P and Hunt, Jonathan J and Pritzel, Alexander and Heess, Nicolas and Erez, Tom and Tassa, Yuval and Silver, David and Wierstra, Daan},
journal={arXiv preprint arXiv:1509.02971},
year={2015}
}
@article{mnih2015human,
title={Human-level control through deep reinforcement learning},
author={Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Rusu, Andrei A and Veness, Joel and Bellemare, Marc G and Graves, Alex and Riedmiller, Martin and Fidjeland, Andreas K and Ostrovski, Georg and others},
journal={Nature},
volume={518},
number={7540},
pages={529--533},
year={2015},
publisher={Nature Research}
}
@article{lenz2015deep,
title={Deep learning for detecting robotic grasps},
author={Lenz, Ian and Lee, Honglak and Saxena, Ashutosh},
journal={The International Journal of Robotics Research},
volume={34},
number={4-5},
pages={705--724},
year={2015},
publisher={SAGE Publications Sage UK: London, England}
}
@article{mnih2013playing,
title={Playing atari with deep reinforcement learning},
author={Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Graves, Alex and Antonoglou, Ioannis and Wierstra, Daan and Riedmiller, Martin},
journal={arXiv preprint arXiv:1312.5602},
year={2013}
}
@article{ba2016layer,
title={Layer normalization},
author={Ba, Jimmy Lei and Kiros, Jamie Ryan and Hinton, Geoffrey E},
journal={arXiv preprint arXiv:1607.06450},
year={2016}
}
@inproceedings{andrychowicz2016learning,
title={Learning to learn by gradient descent by gradient descent},
author={Andrychowicz, Marcin and Denil, Misha and Gomez, Sergio and Hoffman, Matthew W and Pfau, David and Schaul, Tom and de Freitas, Nando},
booktitle={Advances in Neural Information Processing Systems},
pages={3981--3989},
year={2016}
}
@article{ganin2016domain,
title={Domain-adversarial training of neural networks},
author={Ganin, Yaroslav and Ustinova, Evgeniya and Ajakan, Hana and Germain, Pascal and Larochelle, Hugo and Laviolette, Fran{\c{c}}ois and Marchand, Mario and Lempitsky, Victor},
journal={Journal of Machine Learning Research},
volume={17},
number={59},
pages={1--35},
year={2016}
}
@article{van2016wavenet,
title={Wavenet: A generative model for raw audio},
author={van den Oord, A{\"a}ron and Dieleman, Sander and Zen, Heiga and Simonyan, Karen and Vinyals, Oriol and Graves, Alex and Kalchbrenner, Nal and Senior, Andrew and Kavukcuoglu, Koray},
journal={CoRR abs/1609.03499},
year={2016}
}
@inproceedings{zhang2016colorful,
title={Colorful image colorization},
author={Zhang, Richard and Isola, Phillip and Efros, Alexei A},
booktitle={European Conference on Computer Vision},
pages={649--666},
year={2016},
organization={Springer}
}
@inproceedings{zhu2016generative,
title={Generative visual manipulation on the natural image manifold},
author={Zhu, Jun-Yan and Kr{\"a}henb{\"u}hl, Philipp and Shechtman, Eli and Efros, Alexei A},
booktitle={European Conference on Computer Vision},
pages={597--613},
year={2016},
organization={Springer}
}
@inproceedings{ulyanov2016texture,
title={Texture networks: Feed-forward synthesis of textures and stylized images},
author={Ulyanov, Dmitry and Lebedev, Vadim and Vedaldi, Andrea and Lempitsky, Victor},
booktitle={Int. Conf. on Machine Learning (ICML)},
year={2016}
}
@inproceedings{liu2016ssd,
title={SSD: Single shot multibox detector},
author={Liu, Wei and Anguelov, Dragomir and Erhan, Dumitru and Szegedy, Christian and Reed, Scott and Fu, Cheng-Yang and Berg, Alexander C},
booktitle={European Conference on Computer Vision},
pages={21--37},
year={2016},
organization={Springer}
}
@article{iandola2016squeezenet,
title={SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size},
author={Iandola, Forrest N and Han, Song and Moskewicz, Matthew W and Ashraf, Khalid and Dally, William J and Keutzer, Kurt},
journal={arXiv preprint arXiv:1602.07360},
year={2016}
}
@inproceedings{han2016eie,
title={EIE: efficient inference engine on compressed deep neural network},
author={Han, Song and Liu, Xingyu and Mao, Huizi and Pu, Jing and Pedram, Ardavan and Horowitz, Mark A and Dally, William J},
booktitle={Proceedings of the 43rd International Symposium on Computer Architecture},
pages={243--254},
year={2016},
organization={IEEE Press}
}
@article{courbariaux2016binarized,
title={Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1},
author={Courbariaux, Matthieu and Hubara, Itay and Soudry, Daniel and El-Yaniv, Ran and Bengio, Yoshua},
journal={arXiv preprint arXiv:1602.02830},
year={2016}
}
@article{xiong2016dynamic,
title={Dynamic memory networks for visual and textual question answering},
author={Xiong, Caiming and Merity, Stephen and Socher, Richard},
journal={arXiv},
volume={1603},
year={2016}
}
@inproceedings{yang2016stacked,
title={Stacked attention networks for image question answering},
author={Yang, Zichao and He, Xiaodong and Gao, Jianfeng and Deng, Li and Smola, Alex},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={21--29},
year={2016}
}
@article{graves2016hybrid,
title={Hybrid computing using a neural network with dynamic external memory},
author={Graves, Alex and Wayne, Greg and Reynolds, Malcolm and Harley, Tim and Danihelka, Ivo and Grabska-Barwi{\'n}ska, Agnieszka and Colmenarejo, Sergio G{\'o}mez and Grefenstette, Edward and Ramalho, Tiago and Agapiou, John and others},
journal={Nature},
volume={538},
number={7626},
pages={471--476},
year={2016},
publisher={Nature Research}
}
@article{wu2016google,
title={Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation},
author={Wu, Yonghui and Schuster, Mike and Chen, Zhifeng and Le, Quoc V and Norouzi, Mohammad and Macherey, Wolfgang and Krikun, Maxim and Cao, Yuan and Gao, Qin and Macherey, Klaus and others},
journal={arXiv preprint arXiv:1609.08144},
year={2016}
}