AIMC Topic: Humans

Clear Filters Showing 17601 to 17610 of 95995 articles

Quantum-inspired neural network with hierarchical entanglement embedding for matching.

Neural networks : the official journal of the International Neural Network Society
Quantum-inspired neural networks (QNNs) have shown potential in capturing various non-classical phenomena in language understanding, e.g., the emgerent meaning of concept combinations, and represent a leap beyond conventional models in cognitive scie...

Learning extreme expected shortfall and conditional tail moments with neural networks. Application to cryptocurrency data.

Neural networks : the official journal of the International Neural Network Society
We propose a neural networks method to estimate extreme Expected Shortfall, and even more generally, extreme conditional tail moments as functions of confidence levels, in heavy-tailed settings. The convergence rate of the uniform error between the l...

Deep temporal representation learning for language identification.

Neural networks : the official journal of the International Neural Network Society
Language identification (LID) is a key component in downstream tasks. Recently, the self-supervised speech representation learned by Wav2Vec 2.0 (W2V2) has been demonstrated to be very effective for various speech-related tasks. In LID, it is commonl...

VC dimension of Graph Neural Networks with Pfaffian activation functions.

Neural networks : the official journal of the International Neural Network Society
Graph Neural Networks (GNNs) have emerged in recent years as a powerful tool to learn tasks across a wide range of graph domains in a data-driven fashion. Based on a message passing mechanism, GNNs have gained increasing popularity due to their intui...

Rethinking the impact of noisy labels in graph classification: A utility and privacy perspective.

Neural networks : the official journal of the International Neural Network Society
Graph neural networks (GNNs) based on message-passing mechanisms have achieved advanced results in graph classification tasks. However, their generalization performance degrades when noisy labels are present in the training data. Most existing noisy ...

Rethinking density ratio estimation based hyper-parameter optimization.

Neural networks : the official journal of the International Neural Network Society
Hyper-parameter optimization (HPO) aims to improve the performance of machine learning algorithms by identifying appropriate hyper-parameters. By converting the computation of expected improvement into density-ratio estimation problems, existing work...

Enhancing Open-Set Domain Adaptation through Optimal Transport and Adversarial Learning.

Neural networks : the official journal of the International Neural Network Society
Open-Set Domain Adaptation (OSDA) is designed to facilitate the transfer of knowledge from a source domain to a target domain, where the class space of the source is a subset of the target. The primary challenge in OSDA is the identification of share...

Multilevel semantic and adaptive actionness learning for weakly supervised temporal action localization.

Neural networks : the official journal of the International Neural Network Society
Weakly supervised temporal action localization aims to identify and localize action instances in untrimmed videos with only video-level labels. Typically, most methods are based on a multiple instance learning framework that uses a top-K strategy to ...