Artificial Neural Networks and Machine Learning – ICANN 2023

ISBN-13: 9783031442223 / 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, 9 short papers and 9 abstract 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

A Further Exploration of Deep Multi-Agent Reinforcement Learning with Hybrid Action Space.- Air-to-Ground Active Object Tracking via Reinforcement Learning.- Enhancing P300 Detection in Brain-Computer Interfaces with Interpretable Post-Processing of Recurrent Neural Networks.- Group-Agent Reinforcement Learning.- Improving Generalization of Multi-agent Reinforcement Learning through Domain-Invariant Feature Extraction.- Latent-Conditioned Policy Gradient for Multi-Objective Deep Reinforcement Learning.- LIIVSR: A Unidirectional Recurrent Video Super-Resolution Framework with Gaussian Detail Enhancement and Local Information Interaction Modules.- Masked Scale-Recurrent Network for Incomplete Blurred Image Restoration.- Multi-fusion Recurrent Network for Argument Pair Extraction.- Pacesetter Learning For Large Scale Cooperative Multi-Agent Reinforcement Learning.- Stable Learning Algorithm Using Reducibility for Recurrent Neural Networks.- t-ConvESN: Temporal Convolution-Readout for Random Recurrent Neural Networks.- Adaptive Reservoir Neural Gas: An Effective Clustering Algorithm for Addressing Concept Drift in Real-Time Data Streams.- An Intelligent Dynamic Selection System Based on Nearest Temporal Windows for Time Series Forecasting.- Generating Sparse Counterfactual Explanations For Multivariate Time Series.- Graph Neural Network-Based Representation Learning for Medical Time Series.- Knowledge Forcing: Fusing Knowledge-Driven Approaches with LSTM for Time Series Forecasting.- MAGNet: Muti-scale Attention and Evolutionary Graph Structure for Long Sequence Time-Series Forecasting.- MIPCE: Generating Multiple Patches Counterfactual-changing Explanations for Time Series Classification.- Multi-Timestep-Ahead Prediction with Mixture of Experts for Embodied Question Answering.- Rethink the Top-u Attention in Sparse Self-attention for Long Sequence Time-Series Forecasting.- Temporal Attention Signatures for Interpretable Time-Series Prediction.- Time-Series Prediction of Calcium Carbonate Concentration in Flue Gas Desulfurization Equipment by Optimized Echo State Network.- WAG-NAT: Window Attention and Generator Based Non-Autoregressive Transformer for Time Series Forecasting.- A Novel Encoder and Label Assignment for Instance Segmentation.- A Transformer-based Framework for Biomedical Information Retrieval Systems.- A Transformer-Based Method for UAV-View Geo-Localization.- Cross-graph Transformer Network for Temporal Sentence Grounding.- EGCN: A Node Classification Model based on Transformer and Spatial Feature Attention GCN for Dynamic Graph.- Enhance Representational Differentiation Step By Step: A Two-Stage Encoder-Decoder Network for Implicit Discourse Relation Classification.- GenTC: Generative Transformer via Contrastive Learning for Receipt Information Extraction.- Hierarchical Classification for Symmetrized VI Trajectory Based on Lightweight Swin Transformer.- Hierarchical Vision and Language Transformer for Efficient Visual Dialog.- ICDT: Maintaining Interaction Consistency for Deformable Transformer with Multi-scale Features in HOI Detection.- Imbalanced Conditional Conv-Transformer For Mathematical Expression Recognition.- Knowledge Graph  Transformer for Sequential Recommendation.- LorenTzE: Temporal Knowledge Graph Embedding based on Lorentz Transformation.- MFT: Multi-scale Fusion Transformer for Infrared and Visible Image Fusion.- NeuralODE-based Latent Trajectories into AutoEncoder Architecture for Surrogate Modelling of Parametrized High-dimensional Dynamical Systems.- RRecT: Chinese Text Recognition with Radical-enhanced Recognition Transformer.- S2R: Exploring a Double-Win Transformer-Based Framework for Ideal and Blind Super-Resolution.- Self-adapted Positional Encoding in the Transformer Encoder for Named Entity Recognition.- SHGAE: Social Hypergraph AutoEncoder for Friendship Inference.- Temporal Deformable Transformer For Action Localization.- Trans-Cycle: Unpaired Image-to-Image Translation Network by Transformer.