TY - STD TI - Delalleau O, Bengio Y. Shallow vs. deep sum-product networks. In: Advances in neural information processing systems. 2011. p. 666–74. ID - ref1 ER - TY - JOUR AU - Sze, V. AU - Chen, Y. AU - Yang, T. AU - Emer, J. PY - 2017 DA - 2017// TI - Efficient processing of deep neural networks: a tutorial and survey JO - Proc IEEE VL - 105 UR - https://doi.org/10.1109/JPROC.2017.2761740 DO - 10.1109/JPROC.2017.2761740 ID - Sze2017 ER - TY - STD TI - Nwankpa C, Ijomah W, Gachagan A, Marshall S. Activation functions: comparison of trends in practice and research for deep learning. 2018. arXiv:1811.03378. UR - http://arxiv.org/abs/1811.03378 ID - ref3 ER - TY - STD TI - Nair V, Hinton G. Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th international conference on machine learning (ICML-10). 2010. ID - ref4 ER - TY - STD TI - Krizhevsky A, Sutskever I, Hinton G. Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems. 2012. p. 1097–105. ID - ref5 ER - TY - STD TI - Li Y, Ding P, Li B. Training neural networks by using power linear units (PoLUs). 2018. arXiv:1802.00212. UR - http://arxiv.org/abs/1802.00212 ID - ref6 ER - TY - STD TI - Ramachandran P, Zoph B, Le Q. Searching for activation functions. In: Sixth international conference on learning representations (ICLR), Vancouver. 2018. ID - ref7 ER - TY - STD TI - Severyn A, Moschitti A. Unitn: Training deep convolutional neural network for twitter sentiment classification. In: Proceedings of the 9th international workshop on semantic evaluation (SemEval 2015). 2015. https://doi.org/10.18653/v1/s15-2079. ID - ref8 ER - TY - JOUR AU - Li, J. AU - Ng, W. AU - Yeung, D. AU - Chan, P. PY - 2014 DA - 2014// TI - Bi-firing deep neural networks JO - Int J Mach Learn Cybern VL - 5 UR - https://doi.org/10.1007/s13042-013-0198-9 DO - 10.1007/s13042-013-0198-9 ID - Li2014 ER - TY - JOUR AU - Zhao, H. AU - Liu, F. AU - Li, L. AU - Luo, C. PY - 2017 DA - 2017// TI - A novel softplus linear unit for deep convolutional neural networks JO - Appl Intell VL - 48 UR - https://doi.org/10.1007/s10489-017-1028-7 DO - 10.1007/s10489-017-1028-7 ID - Zhao2017 ER - TY - JOUR AU - Liew, S. AU - Khalil-Hani, M. AU - Bakhteri, R. PY - 2016 DA - 2016// TI - Bounded activation functions for enhanced training stability of deep neural networks on visual pattern recognition problems JO - Neurocomputing VL - 216 UR - https://doi.org/10.1016/j.neucom.2016.08.037 DO - 10.1016/j.neucom.2016.08.037 ID - Liew2016 ER - TY - JOUR AU - Sodhi, S. AU - Chandra, P. PY - 2014 DA - 2014// TI - Bi-modal derivative activation function for sigmoidal feedforward networks JO - Neurocomputing VL - 143 UR - https://doi.org/10.1016/j.neucom.2014.06.007 DO - 10.1016/j.neucom.2014.06.007 ID - Sodhi2014 ER - TY - JOUR AU - Nambiar, V. AU - Khalil-Hani, M. AU - Sahnoun, R. AU - Marsono, M. PY - 2014 DA - 2014// TI - Hardware implementation of evolvable block-based neural networks utilizing a cost efficient sigmoid-like activation function JO - Neurocomputing VL - 140 UR - https://doi.org/10.1016/j.neucom.2014.03.018 DO - 10.1016/j.neucom.2014.03.018 ID - Nambiar2014 ER - TY - STD TI - Goodfellow I, Warde-Farley D, Mirza M, Courville A, Bengio Y. Maxout Networks. In: Proceedings of the 30th international conference on machine learning (ICML 2013). 2013. ID - ref14 ER - TY - JOUR AU - Srivastava, N. AU - Hinton, G. AU - Krizhevsky, A. AU - Sutskever, I. AU - Salakhutdinov, R. PY - 2014 DA - 2014// TI - Dropout: a simple way to prevent neural networks from overfitting JO - J Mach Learn Res VL - 15 ID - Srivastava2014 ER - TY - JOUR AU - Wu, X. AU - He, R. AU - Sun, Z. AU - Tan, T. PY - 2015 DA - 2015// TI - A light CNN for deep face representation with noisy labels JO - IEEE Trans Inf Forensics Secur VL - 13 UR - https://doi.org/10.1109/tifs.2018.2833032 DO - 10.1109/tifs.2018.2833032 ID - Wu2015 ER - TY - STD TI - Chang J, Chen Y. Batch-normalized maxout network in network. 2015. arXiv:1511.02583. UR - http://arxiv.org/abs/1511.02583 ID - ref17 ER - TY - STD TI - Cai M, Shi Y, Liu J. Deep maxout neural networks for speech recognition. In: IEEE workshop on automatic speech recognition and understanding 2013. P. 291–6. https://doi.org/10.1109/asru.2013.6707745. ID - ref18 ER - TY - CHAP AU - Park, S. u. n. g. h. e. o. n. AU - Kwak, N. o. j. u. n. PY - 2017 DA - 2017// TI - Analysis on the Dropout Effect in Convolutional Neural Networks BT - Computer Vision – ACCV 2016 PB - Springer International Publishing CY - Cham UR - https://doi.org/10.1007/978-3-319-54184-6_12 DO - 10.1007/978-3-319-54184-6_12 ID - Park2017 ER - TY - JOUR AU - Lecun, Y. AU - Bottou, L. AU - Bengio, Y. AU - Haffner, P. PY - 1998 DA - 1998// TI - Gradient-based learning applied to document recognition JO - Proc IEEE VL - 86 UR - https://doi.org/10.1109/5.726791 DO - 10.1109/5.726791 ID - Lecun1998 ER - TY - BOOK AU - Krizhevsky, A. AU - Hinton, G. PY - 2009 DA - 2009// TI - Learning multiple layers of features from tiny images PB - University of Toronto CY - Toronto ID - Krizhevsky2009 ER - TY - STD TI - Netzer Y, Wang T, Coates A, Bissacco A, Wu B, Ng A. Reading digits in natural images with unsupervised feature learning. In: NIPS workshop on deep learning and unsupervised feature learning. 2011. ID - ref22 ER - TY - STD TI - Jebbara S, Cimiano P. Aspect-based relational sentiment analysis using a stacked neural network architecture. In: Proceedings of the twenty-second European conference on artificial intelligence. 2016. ID - ref23 ER - TY - STD TI - Toth L. Convolutional deep maxout networks for phone recognition. In: Proceedings of the international speech communication association (INTERSPEECH). 2014. ID - ref24 ER - TY - STD TI - Sainath T, Kingsbury B, Mohamed A, Dahl G, Saon G, Soltau H, Beran T, Aravkin A, Ramabhadran B. Improvements to deep convolutional neural networks for LVCSR. In: IEEE workshop on automatic speech recognition and understanding (ASRU). 2013. https://doi.org/10.1109/ASRU.2013.6707749. ID - ref25 ER - TY - JOUR AU - Sainath, T. AU - Kingsbury, B. AU - Saon, G. AU - Soltau, H. AU - Mohamed, A. AU - Dahl, G. AU - Rmabhadran, B. PY - 2015 DA - 2015// TI - Deep convolutional neural networks for large-scale speech tasks JO - Neural Netw VL - 64 UR - https://doi.org/10.1016/j.neunet.2014.08.005 DO - 10.1016/j.neunet.2014.08.005 ID - Sainath2015 ER - TY - STD TI - Yoon K. Convolutional neural networks for sentence classification. In: Conference on empirical methods in natural language processing (EMNLP). 2014. ID - ref27 ER - TY - STD TI - Poria S, Cambria E, Gelbukh A. Deep convolutional neural network textual features and multiple kernel learning for utterance-level multimodal sentiment analysis. In: Conference on empirical methods in natural language processing. 2015. https://doi.org/10.18653/v1/d15-1303. ID - ref28 ER - TY - JOUR AU - Tóth, L. PY - 2015 DA - 2015// TI - Phone recognition with hierarchical convolutional deep maxout networks JO - EURASIP J Audio Speech Music Process VL - 2015 UR - https://doi.org/10.1186/s13636-015-0068-3 DO - 10.1186/s13636-015-0068-3 ID - Tóth2015 ER - TY - STD TI - Tóth L. Combining time-and frequency-domain convolution in convolutional neural network-based phone recognition. In: IEEE international conference on acoustics, speech and signal processing (ICASSP). 2014. https://doi.org/10.1109/icassp.2014.6853584. ID - ref30 ER - TY - STD TI - Deng L, Abdel-Hamid O, Yu D. A deep convolutional neural network using heterogeneous pooling for trading acoustic invariance with phonetic confusion. In: IEEE international conference on acoustics, speech and signal processing (ICASSP). 2013. https://doi.org/10.1109/icassp.2013.6638952. ID - ref31 ER - TY - STD TI - Sainath T, Mohamed A, Kingsbury B, Ramabhadran B. Deep convolutional neural networks for LVCSR. In: IEEE international conference on acoustics, speech and signal processing (ICASSP). 2013. ID - ref32 ER - TY - STD TI - Mikolov T, Sutskever I, Chen K, Corrado G, Dean J. Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems. 2013. p. 3111–9. ID - ref33 ER - TY - STD TI - Johnson R, Zhang T. Effective use of word order for text categorization with convolutional neural networks. In: Proceedings of the 2015 conference of the North American chapter of the association for computational linguistics: human language technologies, Denver. 2015. https://doi.org/10.3115/v1/n15-1011. ID - ref34 ER - TY - STD TI - Xu B, Wang N, Chen T, Li M. Empirical evaluation of rectified activations in convolutional network. 2015. arXiv:1505.00853. UR - http://arxiv.org/abs/1505.00853 ID - ref35 ER - TY - STD TI - Maas A, Hannun A, Ng A. Rectifier nonlinearities improve neural network acoustic models. In: International conference on machine learning (ICML). 2013. ID - ref36 ER - TY - STD TI - He K, Zhang X, Ren S, Sun J. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision. 2015. https://doi.org/10.1109/iccv.2015.123. ID - ref37 ER - TY - JOUR AU - Mishkin, D. AU - Sergievskiy, N. AU - Matas, J. PY - 2017 DA - 2017// TI - Systematic evaluation of convolution neural network advances on the imagenet JO - Comput Vis Image Underst VL - 161 UR - https://doi.org/10.1016/j.cviu.2017.05.007 DO - 10.1016/j.cviu.2017.05.007 ID - Mishkin2017 ER - TY - STD TI - Swietojanski P, Li J, Huang J. Investigation of maxout networks for speech recognition. In: IEEE international conference on acoustics, speech and signal processing (ICASSP). 2014. https://doi.org/10.1109/icassp.2014.6855088. ID - ref39 ER - TY - STD TI - Lin M, Chen Q, Yan S. Network in network. In: Proceedings of the international conference on learning representations (ICLR). 2014. ID - ref40 ER - TY - STD TI - Liao Z, Carneiro G. On the importance of normalisation layers in deep learning with piecewise linear activation units. In: IEEE winter conference on applications of computer vision (WACV). 2016. https://doi.org/10.1109/wacv.2016.7477624. ID - ref41 ER - TY - STD TI - Oyedotun O, Shabayek A, Aouada D, Ottersten B. Improving the capacity of very deep networks with maxout units. In: IEEE international conference on acoustics, speech and signal processing. 2018. https://doi.org/10.1109/icassp.2018.8461436. ID - ref42 ER - TY - JOUR AU - Njikam, A. AU - Zhao, H. PY - 2016 DA - 2016// TI - A novel activation function for multilayer feed-forward neural networks JO - Appl Intell VL - 45 UR - https://doi.org/10.1007/s10489-015-0744-0 DO - 10.1007/s10489-015-0744-0 ID - Njikam2016 ER - TY - STD TI - Goodfellow I, Mirza M, Xiao D, Courville A, Bengio Y. An empirical investigation of catastrophic forgetting in gradient-based neural networks. In: International conference on learning representations (ICLR). 2014. ID - ref44 ER - TY - STD TI - Zhang X, Trmal J, Povey D, Khudanpur S. Improving deep neural network acoustic models using generalized maxout networks. In: IEEE international conference in acoustics, speech and signal processing (ICASSP). 2014. https://doi.org/10.1109/icassp.2014.6853589. ID - ref45 ER - TY - STD TI - Baziotis C, Pelekis N, Doulkeridis C. Datastories at semeval-2017 task 4: Deep lstm with attention for message-level and topic-based sentiment analysis. In: Proceedings of the 11th international workshop on semantic evaluation (SemEval-2017). 2017. https://doi.org/10.18653/v1/s17-2126. ID - ref46 ER - TY - STD TI - Zhang Y, Pezeshki M, Brakel P, Zhang S, Bengio C, Courville A. Towards end-to-end speech recognition with deep convolutional neural networks. In: Sixteenth annual conference of the international speech communication association, interspeech. 2016. https://doi.org/10.21437/interspeech.2016-1446. ID - ref47 ER - TY - STD TI - Branting L, Reeder F, Gold J, Champney T. Graph analytics for healthcare fraud risk estimation. In: Proceedings of the 2016 IEEE/ACM international conference on advances in social networks analysis and mining. 2016. https://doi.org/10.1109/asonam.2016.7752336. ID - ref48 ER - TY - STD TI - Sadiq S, Tao Y, Yan Y, Shyu M. Mining Anomalies in Medicare Big Data Using Patient Rule Induction Method. In: IEEE third international conference on multimedia big data (BigMM). 2017. https://doi.org/10.1109/bigmm.2017.56. ID - ref49 ER - TY - JOUR AU - Herland, M. AU - Khoshgoftaar, T. M. AU - Bauder, R. PY - 2018 DA - 2018// TI - Big Data fraud detection using multiple medicare data sources JO - J Big Data VL - 5 UR - https://doi.org/10.1186/s40537-018-0138-3 DO - 10.1186/s40537-018-0138-3 ID - Herland2018 ER - TY - STD TI - Klambauer G, Unterthiner T, Mayr A, Hochreiter S. Self-normalizing neural networks. In: Advances in neural information processing systems. 2017. p. 971–80. ID - ref51 ER - TY - CHAP AU - Shin, H. C. AU - Orton, M. AU - Collins, D. AU - Doran, S. AU - Leach, M. PY - 2016 DA - 2016// TI - Organ detection using deep learning BT - Medical image recognition, segmentation and parsing PB - Academic Press CY - London UR - https://doi.org/10.1016/b978-0-12-802581-9.00007-x DO - 10.1016/b978-0-12-802581-9.00007-x ID - Shin2016 ER - TY - STD TI - Xiao H, Rasul K, Vollgraf R. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. 2017. arXiv:1708.07747. UR - http://arxiv.org/abs/1708.07747 ID - ref53 ER - TY - STD TI - Huang G, Ramesh M, Berg T, Learned-Miller E. Labeled faces in the wild: a database for studying face recognition in unconstrained environments. 2017. ID - ref54 ER - TY - JOUR AU - Viola, P. AU - Jones, M. PY - 2011 DA - 2011// TI - Rapid object detection using a boosted cascade of simple features JO - Comput Vis Pattern Recognit VL - 34 UR - https://doi.org/10.1109/cvpr.2001.990517 DO - 10.1109/cvpr.2001.990517 ID - Viola2011 ER - TY - CHAP AU - Guo, Y. a. n. d. o. n. g. AU - Zhang, L. e. i. AU - Hu, Y. u. x. i. a. o. AU - He, X. i. a. o. d. o. n. g. AU - Gao, J. i. a. n. f. e. n. g. PY - 2016 DA - 2016// TI - MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition BT - Computer Vision – ECCV 2016 PB - Springer International Publishing CY - Cham UR - https://doi.org/10.1007/978-3-319-46487-9_6 DO - 10.1007/978-3-319-46487-9_6 ID - Guo2016 ER - TY - STD TI - McAuley J, Pandey R, Leskovec J. Inferring networks of substitutable and complementary products. In: Proceedings of the international conference on knowledge discovery and data mining (KDD’15), Sydney, Australia. 2015. https://doi.org/10.1145/2783258.2783381. ID - ref57 ER - TY - STD TI - Heredia B, Khoshgoftaar TM, Prusa JD, Crawford M. Integrating multiple data sources to enhance sentiment prediction. In: 2016 IEEE 2nd international conference on collaboration and internet computing (CIC). 2016. https://doi.org/10.1109/cic.2016.046. ID - ref58 ER - TY - STD TI - Prusa JD, Khoshgoftaar TM. Training convolutional networks on truncated text. In: Proceedings of the IEEE international conference on tools with artificial intelligence. 2017. https://doi.org/10.1109/ictai.2017.00059. ID - ref59 ER - TY - JOUR AU - Go, A. AU - Bhayani, R. AU - Huang, L. PY - 2009 DA - 2009// TI - Twitter sentiment classification using distant supervision JO - CS224N Project Rep Stanford VL - 1 ID - Go2009 ER - TY - STD TI - Centers for Medicare and Medicaid Services. Center for medicare and medicaid services. 2018. https://www.cms.gov/. Accessed 1 Nov 2018. UR - https://www.cms.gov/ ID - ref61 ER - TY - STD TI - Centers for Medicare and Medicaid Services. Medicare provider utilization and payment data: physician and other supplier. 2018. https://www.cms.gov/Research-Statistics-Data-and-Systems/Statistics-Trends-and-Reports/Medicare-Provider-Charge-Data/Physician-and-Other-Supplier.html. Accessed 1 June 2018. UR - https://www.cms.gov/Research-Statistics-Data-and-Systems/Statistics-Trends-and-Reports/Medicare-Provider-Charge-Data/Physician-and-Other-Supplier.html ID - ref62 ER - TY - STD TI - CMS National Provider Identifier Standard. 2018. https://www.cms.gov/Regulations-and-Guidance/Administrative-Simplification/NationalProvIdentStand/. Accessed 4 November 2018. UR - https://www.cms.gov/Regulations-and-Guidance/Administrative-Simplification/NationalProvIdentStand/ ID - ref63 ER - TY - STD TI - CMS. HCPCS—general information. 2018. https://www.cms.gov/Medicare/Coding/MedHCPCSGenInfo/index.html. Accessed 4 Nov 2018. UR - https://www.cms.gov/Medicare/Coding/MedHCPCSGenInfo/index.html ID - ref64 ER - TY - STD TI - Centers for Medicare and Medicaid Services. Medicare provider utilization and payment data: part D prescriber. 2018. https://www.cms.gov/Research-Statistics-Data-and-Systems/Statistics-Trends-and-Reports/Medicare-Provider-Charge-Data/Part-D-Prescriber.html. Accessed 1 June 2018. UR - https://www.cms.gov/Research-Statistics-Data-and-Systems/Statistics-Trends-and-Reports/Medicare-Provider-Charge-Data/Part-D-Prescriber.html ID - ref65 ER - TY - STD TI - CMS. Medicare provider utilization and payment data: referring durable medical equipment, prosthetics, orthotics and supplies. 2018. https://www.cms.gov/Research-Statistics-Data-and-Systems/Statistics-Trends-and-Reports/Medicare-Provider-Charge-Data/DME.html. Accessed 4 Nov 2018. UR - https://www.cms.gov/Research-Statistics-Data-and-Systems/Statistics-Trends-and-Reports/Medicare-Provider-Charge-Data/DME.html ID - ref66 ER - TY - STD TI - Warden P. Speech commands: a dataset for limited-vocabulary speech recognition. 2018. arXiv:1804.03209. UR - http://arxiv.org/abs/1804.03209 ID - ref67 ER - TY - STD TI - Bosch J, Janer J, Fuhrmann F, Herrera P. A comparison of sound segregation techniques for predominant instrument recognition in musical audio signals. In: Proceedings of 13th international society for music information retrieval conference (ISMIR). 2012. ID - ref68 ER - TY - STD TI - Stein M, Abeßer J, Dittmar C, Schuller G. Automatic detection of audio effects in guitar and bass recordings. In: Audio engineering society convention 128. Audio Engineering Society; 2010. ID - ref69 ER - TY - BOOK AU - Zölzer, U. PY - 2011 DA - 2011// TI - DAFX: digital audio effects PB - Wiley CY - New York UR - https://doi.org/10.1002/9781119991298 DO - 10.1002/9781119991298 ID - Zölzer2011 ER - TY - STD TI - Hammer B. Popular datasets over time. 2019. https://www.kaggle.com/benhamner/popular-datasets-over-time/code. Accessed 31 May 2019. UR - https://www.kaggle.com/benhamner/popular-datasets-over-time/code ID - ref71 ER - TY - STD TI - Prusa JD, Khoshgoftaar TM. Designing a better data representation for deep neural networks and text classification. In: IEEE 17th international conference on information reuse and integration (IRI). 2016. https://doi.org/10.1109/iri.2016.61. ID - ref72 ER - TY - STD TI - Zhang X, LeCun Y. Text understanding from scratch. Cornell University, Tech. Rep. 2015. ID - ref73 ER - TY - STD TI - Chollet F. Keras. 2015. https://github.com/keras-team/keras. Accessed 1 Feb 2019. UR - https://github.com/keras-team/keras ID - ref74 ER - TY - STD TI - Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado G, Davis A, Dean J, Devin M, Ghemawat S. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. 2016. ID - ref75 ER - TY - BOOK AU - Berenson, M. L. AU - Levine, D. M. AU - Goldstein, M. PY - 1983 DA - 1983// TI - Intermediate statistical methods and applications: a computer package approach PB - Prentice-Hall, Inc CY - Upper Saddle River UR - https://doi.org/10.2307/2288297 DO - 10.2307/2288297 ID - Berenson1983 ER -