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 EmotionalDialogue 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.

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.