Add CNN section in State of the Art

assets/bibliography.bib

@@ -986,6 +986,7 @@
   ISBN            = 9781728163956,
   publisher       = {IEEE}
 }
+
 @article{kaiser18_discr_autoen_sequen_model,
   author          = {Kaiser, Łukasz and Bengio, Samy},
   title           = {Discrete Autoencoders for Sequence Models},
@@ -1014,3 +1015,141 @@
   eprint          = {1801.09797v1},
   primaryClass    = {cs.LG},
 }
+
+@misc{brownlee_2020,
+  title           = {How Do Convolutional Layers Work in Deep Learning Neural
+                  Networks?},
+  url             = {https://machinelearningmastery.com/convolutional-layers-for-deep-learning-neural-networks/},
+  journal         = {Machine Learning Mastery},
+  author          = {Brownlee, Jason},
+  year            = 2020,
+  month           = {Apr}
+}
+@article{howard17_mobil,
+  author          = {Howard, Andrew G. and Zhu, Menglong and Chen, Bo and
+                  Kalenichenko, Dmitry and Wang, Weijun and Weyand, Tobias and
+                  Andreetto, Marco and Adam, Hartwig},
+  title           = {Mobilenets: Efficient Convolutional Neural Networks for
+                  Mobile Vision Applications},
+  journal         = {CoRR},
+  year            = 2017,
+  url             = {http://arxiv.org/abs/1704.04861v1},
+  abstract        = {We present a class of efficient models called MobileNets
+                  for mobile and embedded vision applications. MobileNets are
+                  based on a streamlined architecture that uses depth-wise
+                  separable convolutions to build light weight deep neural
+                  networks. We introduce two simple global hyper-parameters that
+                  efficiently trade off between latency and accuracy. These
+                  hyper-parameters allow the model builder to choose the right
+                  sized model for their application based on the constraints of
+                  the problem. We present extensive experiments on resource and
+                  accuracy tradeoffs and show strong performance compared to
+                  other popular models on ImageNet classification. We then
+                  demonstrate the effectiveness of MobileNets across a wide
+                  range of applications and use cases including object
+                  detection, finegrain classification, face attributes and large
+                  scale geo-localization.},
+  archivePrefix   = {arXiv},
+  eprint          = {1704.04861v1},
+  primaryClass    = {cs.CV},
+}
+@article{ronneberger15_u_net,
+  author          = {Ronneberger, Olaf and Fischer, Philipp and Brox, Thomas},
+  title           = {U-Net: Convolutional Networks for Biomedical Image
+                  Segmentation},
+  journal         = {CoRR},
+  year            = 2015,
+  url             = {http://arxiv.org/abs/1505.04597v1},
+  abstract        = {There is large consent that successful training of deep
+                  networks requires many thousand annotated training samples. In
+                  this paper, we present a network and training strategy that
+                  relies on the strong use of data augmentation to use the
+                  available annotated samples more efficiently. The architecture
+                  consists of a contracting path to capture context and a
+                  symmetric expanding path that enables precise localization. We
+                  show that such a network can be trained end-to-end from very
+                  few images and outperforms the prior best method (a
+                  sliding-window convolutional network) on the ISBI challenge
+                  for segmentation of neuronal structures in electron
+                  microscopic stacks. Using the same network trained on
+                  transmitted light microscopy images (phase contrast and DIC)
+                  we won the ISBI cell tracking challenge 2015 in these
+                  categories by a large margin. Moreover, the network is fast.
+                  Segmentation of a 512x512 image takes less than a second on a
+                  recent GPU. The full implementation (based on Caffe) and the
+                  trained networks are available at
+                  http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net .},
+  archivePrefix   = {arXiv},
+  eprint          = {1505.04597v1},
+  primaryClass    = {cs.CV},
+}
+@article{yuan18_simpl_convol_gener_networ_next_item_recom,
+  author          = {Yuan, Fajie and Karatzoglou, Alexandros and Arapakis,
+                  Ioannis and Jose, Joemon M and He, Xiangnan},
+  title           = {A Simple Convolutional Generative Network for Next Item
+                  Recommendation},
+  journal         = {CoRR},
+  year            = 2018,
+  url             = {http://arxiv.org/abs/1808.05163v4},
+  abstract        = {Convolutional Neural Networks (CNNs) have been recently
+                  introduced in the domain of session-based next item
+                  recommendation. An ordered collection of past items the user
+                  has interacted with in a session (or sequence) are embedded
+                  into a 2-dimensional latent matrix, and treated as an image.
+                  The convolution and pooling operations are then applied to the
+                  mapped item embeddings. In this paper, we first examine the
+                  typical session-based CNN recommender and show that both the
+                  generative model and network architecture are suboptimal when
+                  modeling long-range dependencies in the item sequence. To
+                  address the issues, we introduce a simple, but very effective
+                  generative model that is capable of learning high-level
+                  representation from both short- and long-range item
+                  dependencies. The network architecture of the proposed model
+                  is formed of a stack of \emph{holed} convolutional layers,
+                  which can efficiently increase the receptive fields without
+                  relying on the pooling operation. Another contribution is the
+                  effective use of residual block structure in recommender
+                  systems, which can ease the optimization for much deeper
+                  networks. The proposed generative model attains
+                  state-of-the-art accuracy with less training time in the next
+                  item recommendation task. It accordingly can be used as a
+                  powerful recommendation baseline to beat in future, especially
+                  when there are long sequences of user feedback.},
+  archivePrefix   = {arXiv},
+  eprint          = {1808.05163v4},
+  primaryClass    = {cs.IR},
+}
+@article{sadr21_novel_deep_learn_method_textual_sentim_analy,
+  author          = {Sadr, Hossein and Solimandarabi, Mozhdeh Nazari and Pedram,
+                  Mir Mohsen and Teshnehlab, Mohammad},
+  title           = {A Novel Deep Learning Method for Textual Sentiment
+                  Analysis},
+  journal         = {CoRR},
+  year            = 2021,
+  url             = {http://arxiv.org/abs/2102.11651v1},
+  abstract        = {Sentiment analysis is known as one of the most crucial
+                  tasks in the field of natural language processing and
+                  Convolutional Neural Network (CNN) is one of those prominent
+                  models that is commonly used for this aim. Although
+                  convolutional neural networks have obtained remarkable results
+                  in recent years, they are still confronted with some
+                  limitations. Firstly, they consider that all words in a
+                  sentence have equal contributions in the sentence meaning
+                  representation and are not able to extract informative words.
+                  Secondly, they require a large number of training data to
+                  obtain considerable results while they have many parameters
+                  that must be accurately adjusted. To this end, a convolutional
+                  neural network integrated with a hierarchical attention layer
+                  is proposed which is able to extract informative words and
+                  assign them higher weight. Moreover, the effect of transfer
+                  learning that transfers knowledge learned in the source domain
+                  to the target domain with the aim of improving the performance
+                  is also explored. Based on the empirical results, the proposed
+                  model not only has higher classification accuracy and can
+                  extract informative words but also applying incremental
+                  transfer learning can significantly enhance the classification
+                  performance.},
+  archivePrefix   = {arXiv},
+  eprint          = {2102.11651},
+  primaryClass    = {cs.CL},
+}