Farkaš / Farkas / Masulli Artificial Neural Networks and Machine Learning – ICANN 2021

30th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 14–17, 2021, Proceedings, Part IV
1. Auflage 2021
ISBN: 978-3-030-86380-7
Verlag: Springer International Publishing
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 703 Seiten, eBook

Reihe: Theoretical Computer Science and General Issues

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.

Zielgruppe

Research

Autoren/Hrsg.

Farkaš, Igor

Farkas, Igor

Masulli, Paolo

Otte, Sebastian

Wermter, Stefan

Inhaltsverzeichnis

Model compression.- Blending Pruning Criteria for Convolutional Neural Networks.- BFRIFP: Brain Functional Reorganization Inspired Filter Pruning.- CupNet - Pruning a network for geometric data.- Pruned-YOLO: Learning Efficient Object Detector Using Model Pruning.- Gator: Customizable Channel Pruning of Neural Networks with Gating.- Multi-task and multi-label learning.- MMF: Multi-Task Multi-Structure Fusion for Hierarchical Image Classification.- GLUNet: Global-Local Fusion U-Net for 2D Medical Image Segmentation.- Textbook Question Answering with Multi-type Question Learning and Contextualized Diagram Representation.- A Multi-Task MRC Framework for Chinese Emotion Cause and Experiencer Extraction.- Fairer Machine Learning Through Multi-objective Evolutionary Learning.- Neural network theory.- Single neurons with delay-based learning can generalise between time-warped patterns.- Estimating Expected Calibration Errors.- LipBAB: Computing exact Lipschitz constantof ReLU networks.- Nonlinear Lagrangean Neural Networks.- Normalization and Regularization Methods.- Energy Conservation in Infinitely Wide Neural-Networks.- Class-Similarity Based Label Smoothing for Confidence Calibration.- Jacobian Regularization for Mitigating Universal Adversarial Perturbations.- Layer-wise Activation Cluster Analysis of CNNs to Detect Out-of-Distribution Samples.- Weight and Gradient Centralization in Deep Neural Networks.- LocalNorm: Robust Image Classification through Dynamically Regularized Normalization.- Channel Capacity of Neural Networks.- RIAP: A method for Effective Receptive Field Rectification.- Curriculum Learning Revisited: Incremental Batch Learning with Instance Typicality Ranking.- Person re-identification.- Interesting Receptive Region and Feature Excitation for Partial Person Re-Identification.- Improved Occluded Person Re-Identification with Multi-feature Fusion.- Joint Weights-averaged and Feature-separated Learning for Person Re-identification.- Semi-Hard Margin Support Vector Machines for Personal Authentication with an Aerial Signature Motion.- Recurrent neural networks.- Dynamic identification of stop locations from GPS trajectories based on their temporal and spatial characteristics.- Separation of Memory and Processing in Dual Recurrent Neural Networks.- Predicting Landfall's Location and Time of a Tropical Cyclone Using Reanalysis Data.- Latent State Inference in a Spatiotemporal Generative Model.- Deep learning models and interpretations for multivariate discrete-valued event sequence prediction.- End-to-End On-Line Multi-Object Tracking on Sparse Point Clouds Using Recurrent Convolutional Networks.- M-ary Hopfield Neural Network based Associative Memory Formulation: Limit-cycle based Sequence Storage and Retrieval.- Training Many-to-Many Recurrent Neural Networks with Target Propagation.- Early Recognition of Ball Catching Success in Clinical Trials with RNN-Based Predictive Classification.- Precise temporal P300 detection in Brain Computer Interface EEG signals using a Long-Short Term Memory.- Noise Quality and Super-Turing Computation in Recurrent Neural Networks.- Reinforcement learning I.- Learning to Plan via a Multi-Step Policy Regression Method.- Behaviour-conditioned policies for cooperative reinforcement learning tasks.- Integrated Actor-Critic for Deep Reinforcement Learning.- Learning to Assist Agents by Observing Them.- Reinforcement Syntactic Dependency Tree Reasoning for Target-Oriented Opinion Word Extraction.- Learning distinct strategies for heterogeneous cooperative multi-agent reinforcement learning.- MAT-DQN: Toward Interpretable Multi-Agent Deep Reinforcement Learning for Coordinated Activities.- Selection-Expansion: a unifying framework for motion-planning and diversity search algorithms.- A Hand Gesture Recognition System using EMG and Reinforcement Learning: a Q-Learning Approach.- Reinforcement learning II.- Reinforcement learning for the privacy preservation and manipulation of eye tracking data.- Reinforcement Symbolic Learning.- Deep Reinforcement Learning for Job Scheduling on Cluster.- Independent Deep Deterministic Policy Gradient Reinforcement Learning in Cooperative Multiagent Pursuit Games.- Avoid Overfitting in Deep Reinforcement Learning: Increasing Robustness through Decentralized Control.- Advances in Adaptive Skill Acquisition.- Aspect-Based Sentiment Classification with Reinforcement Learning and Local Understanding.- Latent dynamics for artefact-free character animation via data-driven reinforcement learning.- Intrinsic Motivation Model Based on Reward Gating.