Artificial Neural Networks and Machine Learning – ICANN 2023

TRAMA

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.

SOMMARIO

A Comparative Study of Sentence Embedding Models for Assessing Semantic Variation.- A Deep Learning based Method for Generating Holographic Acoustic Fields from Phased Transducer Arrays.- A Depth-guided Attention Strategy for Crowd Counting.- A Noise Convolution Network for Tampering Detection.- Attention-based Feature Interaction Deep Factorization Machine for CTR Prediction.- Block-level Stiffness Analysis of Residual Networks.- CKNA: Kernel Hyperparameters Optimization Method for Group-wise CNNs.- Conditional Convolution Residual Network for Efficient Super-Resolution.- Cross Attention with Deep Local Features for Few-shot Image Classification.- Deep Video Compression Based on 3D Convolution Artifacts Removal and Attention Compression Module.- Deep-learning Based Three Channel Defocused Projection Profilometry.- Depthwise Convolution with Channel Mixer: Rethinking MLP in MetaFormer for Faster and More Accurate Vehicle Detection.- DLUIO: Detecting Useful Investor Opinions by Deep Learning.- Dynamic obstacle avoidance for unmanned aerial vehicle using dynamic vision sensor.- Empirical Study on the Effect of Residual Networks on the Expressiveness of Linear Regions.- Energy Complexity Model for Convolutional Neural Networks.- Enhancing the Interpretability of Deep Multi-Agent Reinforcement Learning via Neural Logic Reasoning.- Evidential Robust Deep Learning for Noisy Text2text Question Classification.- FBPFormer: Dynamic Convolutional Transformer for Global-Local-Contexual Facial Beauty Prediction.- Heavy-Tailed Regularization of Weight Matrices in Deep Neural Networks.- Interaction of Generalization and Out-of-Distribution Detection Capabilities in Deep Neural Networks.- Long-distance Pipeline Intrusion Warning Based on Environment Embedding From Distributed Optical Fiber Sensing.- LSA3D: Lightweight Separate Asynchronous 3D Convolutional Neural Network for Gait Recognition.- MADNet: EEG-based Depression Detection using a Deep Convolution Neural Network Framework with Multi-dimensional Attention.- Maintenance automation using deep learning methods a case study from the aerospace industry.- MCASleepNet: Multimodal channel attention-based deep neural network for automatic sleep staging.- Multi-label Image Deep Hashing with Hybrid Loss of Global Center and Local Alignment.- Multi-relation Representation Learning based Deep Network for Patent Classification.- One Hip Wonder: 1D-CNNs Reduce Sensor Requirements for Everyday Gait Analysis.- Patches Channel Attention For Human Sitting Posture Recognition.- RA-Net: A Deep Learning Approach based on Residual Structure and Attention Mechanism for Image Copy-move Forgery Detection.- Rethinking CNN Architectures in Transformer Detectors.- Robustness of Biologically-inspired filter-based ConvNet to Signal Perturbation.- Self-Supervised Graph Convolution for Video Moment Retrieval.- Siamese Network based on MLP and Multi-head Cross Attention for Visual Object Tracking.- Taper Residual Dense Network for Audio Super-Resolution.- VPNDroid: Malicious Android VPN detection using a CNN-RF method.- Who breaks early, looses: goal oriented training of deep neural networks based on port Hamiltonian dynamics.- BLR:A multi-modal sentiment analysis model.- Detecting Negative Sentiment on Sarcastic Tweets for Sentiment Analysis.- Local or Global: The Variation in the Encoding of Style Across Sentiment and Formality.- Prompt-oriented Fine-tuning Dual Bert for Aspect-Based Sentiment Analysis.- Towards Energy-Efficient Sentiment Classification with Spiking Neural Networks.- Using Masked Language Modeling to Enhance BERT-based Aspect-Based Sentiment Analysis for Affective Token Prediction.

ALTRE INFORMAZIONI

• Condizione: Nuovo
• ISBN: 9783031442032
• Collana: Lecture Notes in Computer Science
• Dimensioni: 235 x 155 mm
• Formato: Brossura
• Illustration Notes: XXXIV, 545 p. 177 illus., 163 illus. in color.
• Pagine Arabe: 545
• Pagine Romane: xxxiv