Artificial Neural Networks and Machine Learning – ICANN 2021

1. Front Matter

   Pages i-xxiv

   PDF

2. Model Compression

   1. Front Matter

      Pages 1-1

      PDF

   2. Blending Pruning Criteria for Convolutional Neural Networks

      • Wei He, Zhongzhan Huang, Mingfu Liang, Senwei Liang, Haizhao Yang

      Pages 3-15

   3. BFRIFP: Brain Functional Reorganization Inspired Filter Pruning

      • Shoumeng Qiu, Yuzhang Gu, Xiaolin Zhang

      Pages 16-28

   4. CupNet – Pruning a Network for Geometric Data

      • Raoul Heese, Lukas Morand, Dirk Helm, Michael Bortz

      Pages 29-33

   5. Pruned-YOLO: Learning Efficient Object Detector Using Model Pruning

      • Jiacheng Zhang, Pingyu Wang, Zhicheng Zhao, Fei Su

      Pages 34-45

   6. Gator: Customizable Channel Pruning of Neural Networks with Gating

      • Eli Passov, Eli O. David, Nathan S. Netanyahu

      Pages 46-58

3. Multi-task and Multi-label Learning

   1. Front Matter

      Pages 59-59

      PDF

   2. MMF: Multi-task Multi-structure Fusion for Hierarchical Image Classification

      • Xiaoni Li, Yucan Zhou, Yu Zhou, Weiping Wang

      Pages 61-73

   3. GLUNet: Global-Local Fusion U-Net for 2D Medical Image Segmentation

      • Ning Wang, Hongyan Quan

      Pages 74-85

   4. Textbook Question Answering with Multi-type Question Learning and Contextualized Diagram Representation

      • Jianwei He, Xianghua Fu, Zi Long, Shuxin Wang, Chaojie Liang, Hongbin Lin

      Pages 86-98

   5. A Multi-Task MRC Framework for Chinese Emotion Cause and Experiencer Extraction

      • Haoda Qian, Qiudan Li, Zaichuan Tang

      Pages 99-110

   6. Fairer Machine Learning Through Multi-objective Evolutionary Learning

      • Qingquan Zhang, Jialin Liu, Zeqi Zhang, Junyi Wen, Bifei Mao, Xin Yao

      Pages 111-123

4. Neural Network Theory

   1. Front Matter

      Pages 125-125

      PDF

   2. Single Neurons with Delay-Based Learning Can Generalise Between Time-Warped Patterns

      • Joshua Arnold, Peter Stratton, Janet Wiles

      Pages 127-138

   3. Estimating Expected Calibration Errors

      • Nicolas Posocco, Antoine Bonnefoy

      Pages 139-150

   4. LipBaB: Computing Exact Lipschitz Constant of ReLU Networks

      • Aritra Bhowmick, Meenakshi D’Souza, G. Srinivasa Raghavan

      Pages 151-162

   5. Nonlinear Lagrangean Neural Networks

      • Roseli S. Wedemann, Angel Ricardo Plastino

      Pages 163-173

5. Normalization and Regularization Methods

   1. Front Matter

      Pages 175-175

      PDF

   2. Energy Conservation in Infinitely Wide Neural-Networks

      • Shu Eguchi, Takafumi Amaba

      Pages 177-189

The proceedings set LNCS 12891, LNCS 12892, LNCS 12893, LNCS 12894 and LNCS 12895 constitute the proceedings of the 30th International Conference on Artificial Neural Networks, ICANN 2021, held in Bratislava, Slovakia, in September 2021.* The total of 265 full papers presented in these proceedings was carefully reviewed and selected from 496 submissions, and organized in 5 volumes.

In this volume, the papers focus on topics such as model compression, multi-task and multi-label learning, neural network theory, normalization and regularization methods, person re-identification, recurrent neural networks, and reinforcement learning.

*The conference was held online 2021 due to the COVID-19 pandemic.

• artificial intelligence
• computer hardware
• computer networks
• computer science
• computer systems
• computer vision
• databases
• education
• engineering
• image analysis
• image processing
• internet
• learning
• machine learning
• mathematics
• network architecture
• network protocols
• neural networks
• reinforcement learning
• signal processing

• Comenius University in Bratislava, Bratislava, Slovakia

  Igor Farkaš

• iMotions A/S, Copenhagen, Denmark

  Paolo Masulli

• University of Tübingen, Tübingen, Germany

  Sebastian Otte

• Universität Hamburg, Hamburg, Germany

  Stefan Wermter

Policies and ethics