Artificial Neural Networks and Machine Learning – ICANN 2019: Deep Learning

1. Parameters Optimisation

   1. Post-synaptic Potential Regularization Has Potential

      • Enzo Tartaglione, Daniele Perlo, Marco Grangetto

      Pages 187-200

   2. 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

   3. Sign Based Derivative Filtering for Stochastic Gradient Descent

      • Konstantin Berestizshevsky, Guy Even

      Pages 208-219

   4. Architecture-Aware Bayesian Optimization for Neural Network Tuning

      • Anders Sjöberg, Magnus Önnheim, Emil Gustavsson, Mats Jirstrand

      Pages 220-231

   5. Non-convergence and Limit Cycles in the Adam Optimizer

      • Sebastian Bock, Martin Weiß

      Pages 232-243

2. Pruning Networks

   1. Front Matter

      Pages 245-245

      PDF

   2. Learning Internal Dense But External Sparse Structures of Deep Convolutional Neural Network

      • Yiqun Duan, Chen Feng

      Pages 247-262

   3. Using Feature Entropy to Guide Filter Pruning for Efficient Convolutional Networks

      • Yun Li, Luyang Wang, Sifan Peng, Aakash Kumar, Baoqun Yin

      Pages 263-274

   4. Simultaneously Learning Architectures and Features of Deep Neural Networks

      • Tinghuai Wang, Lixin Fan, Huiling Wang

      Pages 275-287

   5. Learning Sparse Hidden States in Long Short-Term Memory

      • Niange Yu, Cornelius Weber, Xiaolin Hu

      Pages 288-298

   6. Multi-objective Pruning for CNNs Using Genetic Algorithm

      • Chuanguang Yang, Zhulin An, Chao Li, Boyu Diao, Yongjun Xu

      Pages 299-305

   7. Dynamically Sacrificing Accuracy for Reduced Computation: Cascaded Inference Based on Softmax Confidence

      • Konstantin Berestizshevsky, Guy Even

      Pages 306-320

   8. Light-Weight Edge Enhanced Network for On-orbit Semantic Segmentation

      • Junxing Hu, Ling Li, Yijun Lin, Fengge Wu, Junsuo Zhao

      Pages 321-333

   9. Local Normalization Based BN Layer Pruning

      • Yuan Liu, Xi Jia, Linlin Shen, Zhong Ming, Jinming Duan

      Pages 334-346

3. Search for an Optimal Architecture

   1. Front Matter

      Pages 347-347

      PDF

   2. On Practical Approach to Uniform Quantization of Non-redundant Neural Networks

      • Alexander Goncharenko, Andrey Denisov, Sergey Alyamkin, Evgeny Terentev

      Pages 349-360

   3. Residual Learning for FC Kernels of Convolutional Network

      • Alexey Alexeev, Yuriy Matveev, Anton Matveev, Dmitry Pavlenko

      Pages 361-372

   4. A Novel Neural Network-Based Symbolic Regression Method: Neuro-Encoded Expression Programming

      • Aftab Anjum, Fengyang Sun, Lin Wang, Jeff Orchard

      Pages 373-386

   5. Compute-Efficient Neural Network Architecture Optimization by a Genetic Algorithm

      • Sebastian Litzinger, Andreas Klos, Wolfram Schiffmann

      Pages 387-392

   6. Controlling Model Complexity in Probabilistic Model-Based Dynamic Optimization of Neural Network Structures

      • Shota Saito, Shinichi Shirakawa

      Pages 393-405

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. 

• artificial intelligence
• classification
• clustering
• computational linguistics
• computer networks
• Human-Computer Interaction (HCI)
• image processing
• image reconstruction
• image segmentation
• imaging systems
• learning algorithms
• machine learning
• neural networks
• recurrent neural networks
• robotics
• semantics
• sensors
• signal processing
• Support Vector Machines (SVM)
• user interfaces

• Helmholtz Zentrum München - Deutsches Forschungszentrum für Gesundheit und Umwelt (GmbH), Neuherberg, Germany

  Igor V. Tetko, Pavel Karpov, Fabian Theis

• Institute of Computer Science, Czech Academy of Sciences, Prague 8, Czech Republic

  Věra Kůrková

Policies and ethics