Titlebook: Artificial Neural Networks and Machine Learning – ICANN 2023; 32nd International C Lazaros Iliadis,Antonios Papaleonidas,Chrisina Jay Confe

Astigmatism

Ordnance

,Traglasts?tze der Plastizit?tstheorie,gineering problems. In recent years, with the rapid development of deep learning techniques, physics-informed neural networks (PINNs) have been successfully applied to solve partial differential equations and physical field simulations. Based on physical constraints, PINNs have received a lot of att

minion

https://doi.org/10.1007/978-3-031-44192-9artificial neural networks (NN); machine learning; deep learning; federated learning; convolutional neur

雜色

978-3-031-44191-2The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerl

Canopy

Artificial Neural Networks and Machine Learning – ICANN 2023978-3-031-44192-9Series ISSN 0302-9743 Series E-ISSN 1611-3349

前奏曲

A Multi-Task Instruction with Chain of Thought Prompting Generative Framework for Few-Shot Named Enning has been successful in few-shot NER by using prompts to guide the labeling process and increase efficiency. However, previous prompt-based methods for few-shot NER have limitations such as high computational complexity and insufficient few-shot capability. To address these concerns, we propose

Laconic

ANODE-GAN: Incomplete Time Series Imputation by Augmented Neural ODE-Based Generative Adversarial N missing values, including statistical, machine learning, and deep learning approaches. However, these methods either involve multi-steps, neglect temporal information, or are incapable of imputing missing data at desired time points. To overcome these limitations, this paper proposes a novel genera

滲透

Boosting Adversarial Transferability Through Intermediate Feature,covered that adversarial samples can perform black-box attacks, that is, adversarial samples generated on the original model can cause models with different structures from the original model to misidentify. A large number of methods have recently been proposed to improve the transferability of adve

壓碎

DaCon: Multi-Domain Text Classification Using Domain Adversarial Contrastive Learning,ate-of-the-art approaches address the MDTC problem using a shared-private model design (i.e., a shared feature encoder and multiple domain-specific encoders) which requires massive amounts of labeled data. However, some domains in real-world scenarios lack sufficient labeled data, resulting in signi

Comprise

,Exploring the?Role of?Recursive Convolutional Layer in?Generative Adversarial Networks,ological systems, in which feedback connections are prevalent, different studies investigated their impact on artificial neural networks. These studies have shown that feedback connections improve performance in tasks such as image classification and segmentation. Motivated by this insight, in this