Artificial Neural Networks and Machine Learning – ICANN 2019: Deep Learning: 28th International Conference on Artificial Neural Networks, Munich, Germany, September 17–19, 2019, Proceedings, Part II

Description

The proceedings set LNCS 11727, 11728, 11729, 11730, and 11731 constitute the proceedings of the 28th International Conference on Artificial Neural Networks, ICANN 2019, held in Munich, Germany, in September 2019. The total of 277 full papers and 43 short papers presented in these proceedings was carefully reviewed and selected from 494 submissions. They were organized in 5 volumes focusing on theoretical neural computation; deep learning; image processing; text and time series; and workshop and special sessions. Front Matter ....Pages i-xxx Front Matter ....Pages 1-1 Adaptive Graph Fusion for Unsupervised Feature Selection (Sijia Niu, Pengfei Zhu, Qinghua Hu, Hong Shi)....Pages 3-15 Unsupervised Feature Selection via Local Total-Order Preservation (Rui Ma, Yijie Wang, Li Cheng)....Pages 16-28 Discrete Stochastic Search and Its Application to Feature-Selection for Deep Relational Machines (Tirtharaj Dash, Ashwin Srinivasan, Ramprasad S. Joshi, A. Baskar)....Pages 29-45 Joint Dictionary Learning for Unsupervised Feature Selection (Yang Fan, Jianhua Dai, Qilai Zhang, Shuai Liu)....Pages 46-58 Comparison Between Filter Criteria for Feature Selection in Regression (Alexandra Degeest, Michel Verleysen, Benoît Frénay)....Pages 59-71 CancelOut: A Layer for Feature Selection in Deep Neural Networks (Vadim Borisov, Johannes Haug, Gjergji Kasneci)....Pages 72-83 Adaptive-\(L_2\) Batch Neural Gas (Nicomedes L. Cavalcanti Jr., Marcelo Rodrigo Portela Ferreira, Francisco de Assis Tenorio de Carvalho)....Pages 84-95 Application of Self Organizing Map to Preprocessing Input Vectors for Convolutional Neural Network (Hiroshi Dozono, Masafumi Tanaka)....Pages 96-100 Front Matter ....Pages 101-101 Hierarchical Reinforcement Learning with Unlimited Recursive Subroutine Calls (Yuuji Ichisugi, Naoto Takahashi, Hidemoto Nakada, Takashi Sano)....Pages 103-114 Automatic Augmentation by Hill Climbing (Ricardo Cruz, Joaquim F. Pinto Costa, Jaime S. Cardoso)....Pages 115-124 Learning Camera-Invariant Representation for Person Re-identification (Shizheng Qin, Kangzheng Gu, Lecheng Wang, Lizhe Qi, Wenqiang Zhang)....Pages 125-137 PA-RetinaNet: Path Augmented RetinaNet for Dense Object Detection (Guanghua Tan, Zijun Guo, Yi Xiao)....Pages 138-149 Front Matter ....Pages 151-151 Singular Value Decomposition and Neural Networks (Bernhard Bermeitinger, Tomas Hrycej, Siegfried Handschuh)....Pages 153-164 PCI: Principal Component Initialization for Deep Autoencoders (Aiga Suzuki, Hidenori Sakanashi)....Pages 165-169 Improving Weight Initialization of ReLU and Output Layers (Diego Aguirre, Olac Fuentes)....Pages 170-184 Front Matter ....Pages 185-185 Post-synaptic Potential Regularization Has Potential (Enzo Tartaglione, Daniele Perlo, Marco Grangetto)....Pages 187-200 A Novel Modification on the Levenberg-Marquardt Algorithm for Avoiding Overfitting in Neural Network Training (Serdar Iplikci, Batuhan Bilgi, Ali Menemen, Bedri Bahtiyar)....Pages 201-207 Sign Based Derivative Filtering for Stochastic Gradient Descent (Konstantin Berestizshevsky, Guy Even)....Pages 208-219 Architecture-Aware Bayesian Optimization for Neural Network Tuning (Anders Sjöberg, Magnus Önnheim, Emil Gustavsson, Mats Jirstrand)....Pages 220-231 Non-convergence and Limit Cycles in the Adam Optimizer (Sebastian Bock, Martin Weiß)....Pages 232-243 Front Matter ....Pages 245-245 Learning Internal Dense But External Sparse Structures of Deep Convolutional Neural Network (Yiqun Duan, Chen Feng)....Pages 247-262 Using Feature Entropy to Guide Filter Pruning for Efficient Convolutional Networks (Yun Li, Luyang Wang, Sifan Peng, Aakash Kumar, Baoqun Yin)....Pages 263-274 Simultaneously Learning Architectures and Features of Deep Neural Networks (Tinghuai Wang, Lixin Fan, Huiling Wang)....Pages 275-287 Learning Sparse Hidden States in Long Short-Term Memory (Niange Yu, Cornelius Weber, Xiaolin Hu)....Pages 288-298 Multi-objective Pruning for CNNs Using Genetic Algorithm (Chuanguang Yang, Zhulin An, Chao Li, Boyu Diao, Yongjun Xu)....Pages 299-305 Dynamically Sacrificing Accuracy for Reduced Computation: Cascaded Inference Based on Softmax Confidence (Konstantin Berestizshevsky, Guy Even)....Pages 306-320 Light-Weight Edge Enhanced Network for On-orbit Semantic Segmentation (Junxing Hu, Ling Li, Yijun Lin, Fengge Wu, Junsuo Zhao)....Pages 321-333 Local Normalization Based BN Layer Pruning (Yuan Liu, Xi Jia, Linlin Shen, Zhong Ming, Jinming Duan)....Pages 334-346 Front Matter ....Pages 347-347 On Practical Approach to Uniform Quantization of Non-redundant Neural Networks (Alexander Goncharenko, Andrey Denisov, Sergey Alyamkin, Evgeny Terentev)....Pages 349-360 Residual Learning for FC Kernels of Convolutional Network (Alexey Alexeev, Yuriy Matveev, Anton Matveev, Dmitry Pavlenko)....Pages 361-372 A Novel Neural Network-Based Symbolic Regression Method: Neuro-Encoded Expression Programming (Aftab Anjum, Fengyang Sun, Lin Wang, Jeff Orchard)....Pages 373-386 Compute-Efficient Neural Network Architecture Optimization by a Genetic Algorithm (Sebastian Litzinger, Andreas Klos, Wolfram Schiffmann)....Pages 387-392 Controlling Model Complexity in Probabilistic Model-Based Dynamic Optimization of Neural Network Structures (Shota Saito, Shinichi Shirakawa)....Pages 393-405 Front Matter ....Pages 407-407 Predictive Uncertainty Estimation with Temporal Convolutional Networks for Dynamic Evolutionary Optimization (Almuth Meier, Oliver Kramer)....Pages 409-421 Sparse Recurrent Mixture Density Networks for Forecasting High Variability Time Series with Confidence Estimates (Narendhar Gugulothu, Easwar Subramanian, Sanjay P. Bhat)....Pages 422-433 A Multitask Learning Neural Network for Short-Term Traffic Speed Prediction and Confidence Estimation (Yanyun Tao, Xiang Wang, Yuzhen Zhang)....Pages 434-449 Front Matter ....Pages 451-451 Central-Diffused Instance Generation Method in Class Incremental Learning (Mingyu Liu, Yijie Wang)....Pages 453-465 Marginal Replay vs Conditional Replay for Continual Learning (Timothée Lesort, Alexander Gepperth, Andrei Stoian, David Filliat)....Pages 466-480 Simplified Computation and Interpretation of Fisher Matrices in Incremental Learning with Deep Neural Networks (Alexander Gepperth, Florian Wiech)....Pages 481-494 Active Learning for Image Recognition Using a Visualization-Based User Interface (Christian Limberg, Kathrin Krieger, Heiko Wersing, Helge Ritter)....Pages 495-506 Basic Evaluation Scenarios for Incrementally Trained Classifiers (Rudolf Szadkowski, Jan Drchal, Jan Faigl)....Pages 507-517 Embedding Complexity of Learned Representations in Neural Networks (Tomáš Kuzma, Igor Farkaš)....Pages 518-528 Front Matter ....Pages 529-529 Joint Metric Learning on Riemannian Manifold of Global Gaussian Distributions (Qinqin Nie, Bin Zhou, Pengfei Zhu, Qinghua Hu, Hao Cheng)....Pages 531-542 Multi-task Sparse Regression Metric Learning for Heterogeneous Classification (Haotian Wu, Bin Zhou, Pengfei Zhu, Qinghua Hu, Hong Shi)....Pages 543-553 Fast Approximate Geodesics for Deep Generative Models (Nutan Chen, Francesco Ferroni, Alexej Klushyn, Alexandros Paraschos, Justin Bayer, Patrick van der Smagt)....Pages 554-566 Spatial Attention Network for Few-Shot Learning (Xianhao He, Peng Qiao, Yong Dou, Xin Niu)....Pages 567-578 Routine Modeling with Time Series Metric Learning (Paul Compagnon, Grégoire Lefebvre, Stefan Duffner, Christophe Garcia)....Pages 579-592 Front Matter ....Pages 593-593 Leveraging Domain Knowledge for Reinforcement Learning Using MMC Architectures (Rajkumar Ramamurthy, Christian Bauckhage, Rafet Sifa, Jannis Schücker, Stefan Wrobel)....Pages 595-607 Conditions for Unnecessary Logical Constraints in Kernel Machines (Francesco Giannini, Marco Maggini)....Pages 608-620 HiSeqGAN: Hierarchical Sequence Synthesis and Prediction (Yun-Chieh Tien, Chen-Min Hsu, Fang Yu)....Pages 621-638 DeepEX: Bridging the Gap Between Knowledge and Data Driven Techniques for Time Series Forecasting (Muhammad Ali Chattha, Shoaib Ahmed Siddiqui, Mohsin Munir, Muhammad Imran Malik, Ludger van Elst, Andreas Dengel et al.)....Pages 639-651 Front Matter ....Pages 653-653 Transferable Adversarial Cycle Alignment for Domain Adaption (Yingcan Wei)....Pages 655-672 Evaluation of Domain Adaptation Approaches for Robust Classification of Heterogeneous Biological Data Sets (Michael Schneider, Lichao Wang, Carsten Marr)....Pages 673-686 Named Entity Recognition for Chinese Social Media with Domain Adversarial Training and Language Modeling (Yong Xu, Qi Lu, Muhua Zhu)....Pages 687-699 Deep Domain Knowledge Distillation for Person Re-identification (Junjie Yan)....Pages 700-713 A Study on Catastrophic Forgetting in Deep LSTM Networks (Monika Schak, Alexander Gepperth)....Pages 714-728 Front Matter ....Pages 729-729 A Label-Specific Attention-Based Network with Regularized Loss for Multi-label Classification (Xiangyang Luo, Xiangying Ran, Wei Sun, Yunlai Xu, Chongjun Wang)....Pages 731-742 An Empirical Study of Multi-domain and Multi-task Learning in Chinese Named Entity Recognition (Yun Hu, Mingxue Liao, Pin Lv, Changwen Zheng)....Pages 743-754 Filter Method Ensemble with Neural Networks (Anuran Chakraborty, Rajonya De, Agneet Chatterjee, Friedhelm Schwenker, Ram Sarkar)....Pages 755-765 Dynamic Centroid Insertion and Adjustment for Data Sets with Multiple Imbalanced Classes (Evandro J. R. Silva, Cleber Zanchettin)....Pages 766-778 Increasing the Generalisaton Capacity of Conditional VAEs (Alexej Klushyn, Nutan Chen, Botond Cseke, Justin Bayer, Patrick van der Smagt)....Pages 779-791 Playing the Large Margin Preference Game (Mirko Polato, Guglielmo Faggioli, Ivano Lauriola, Fabio Aiolli)....Pages 792-804 Back Matter ....Pages 805-807