Artificial Neural Networks and Machine Learning – ICANN 2023

ISBN-13: 9783031442001 / Angielski / Miękka / 2023

Opis

The 10-volume set LNCS 14254-14263 constitutes the proceedings of the 32nd International Conference on Artificial Neural Networks and Machine Learning, ICANN 2023, which took place in Heraklion, Crete, Greece, during September 26–29, 2023.The 426 full papers and 9 short papers included in these proceedings were carefully reviewed and selected from 947 submissions. ICANN is a dual-track conference, featuring tracks in brain inspired computing on the one hand, and machine learning on the other, with strong cross-disciplinary interactions and applications.

Spis treści

MEA-TransUNet: a Multiple External Attention Network for Multi-Organ Segmentation.- Membership-Grade Based Prototype Rectification for Fine-Grained Few-Shot Classification.- Multi-grained Aspect Fusion for Review Response Generation.- Multiple Object Tracking based on Variable GIoU-Embedding Matrix and Kalman Filter Compensation.- Multi-relation Identification for Few-shot Document-level Relation Extraction.- Multi-Task Learning for Mongolian Morphological Analysis.- Multi-task Pre-training for Lhasa-Tibetan Speech Recognition.- Mutual Information Dropout: Mutual Information Can  Be All You Need.- Non-Outlier Pseudo-Labeling for Short Text Clustering.- Optimal Node Embedding Dimension Selection Using Overall Entropy.- PairEE: A Novel Pairing-Scoring Approach for Better Overlapping Event Extraction.- PCB Component Rotation Detection Based on Polarity Identifier Attention.- PCDialogEval: Persona and Context Aware Emotional Dialogue Evaluation.- PlantDet: A benchmark for Plant Detection in the Three-Rivers-Source Region.- PO-DARTS: Post-Optimizing the Architectures Searched by Differentiable Architecture Search Algorithms.- Predicting high vs low mother-baby synchrony with GRU-based ensemble models.- Properties of the weighted and robust implicitly weighted correlation coefficients.- PSML: Prototype-Based OSSL Framework for Multi-Information Mining.- Pure Physics-Informed Echo State Network of ODE Solution Replicator.- RegionRel:A Framework for Jointly Extracting Relational Triplets by Performing Sub-tasks by Region.- Robustness to Variability and Asymmetry of In-memory On-chip Training.- Selecting Distinctive-Variant Training Samples Base on Intra-class Similarity.- Semantic Information Mining and Fusion Method for Bot Detection.- Semilayer-Wise Partial Quantization without Accuracy Degradation or Back Propagation.- ShadowGAN for Line Drawings Shadow Generation.- Ship Attitude Prediction Based on Dynamic Sliding Window and EEMD-SSA-BiLSTM.- Solving Math Word Problem with External Knowledge and Entailment Loss.- Spatially Invariant and Frequency-Aware CycleGAN for Unsupervised MR-to-CT Synthesis.- Spatio-temporal Attention Model with Prior Knowledge for Solar Wind Speed Prediction.- Spatiotemporal model with attention mechanism for ENSO Predictions.- SPM-Diffusion for Temperature Prediction.- S-SOLVER: Numerically stable adaptive step size solver for neural ODEs.- TableSF: A Structural Bias Framework for Table-to-Text Generation.- TCS-LipNet:Temporal & Channel & Spatial Attention-based Lip Reading Network.- The Dynamic Selection of Combination Methods in Classifier Ensembles by Region of Competence.- The progressive detectors and discriminative feature descriptors combining global and local information.- Towards Better Dialogue Utterance Rewriting via a Gated Span-Copy Mechanism.- TSP Combination Optimization with Semi-local Attention Mechanism.- UDCGN: Uncertainty-Driven Cross-Guided Network for Depth Completion of Transparent Objects.- Use of Machine Learning Algorithms to Analyze the Digit Recognizer Problem in an Effective Manner.- Vulnerability Analysis of Continuous Prompts for Pre-trained Language Models.