Results 201 to 210 of about 127,617 (265)

HPoolGCL: Augmentation‐Free Cross‐Granularity Graph Contrastive Learning With Hierarchical Pooling

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Graph contrastive learning (GCL) has emerged as a dominant paradigm for self‐supervised representation learning for attributed graph data. However, existing GCL methods heavily rely on empirical graph data augmentation, which may distort intrinsic graph semantics and produce poor generalisation without carefully chosen or designed augmentation
Fenglin Cen, Shijie Liu, Quan Feng, Tiantian He, Ji Xu   +4 more
wiley   +1 more source

Training convolutional neural networks with the Forward-Forward Algorithm. [PDF]

Sci Rep
Scodellaro R, Kulkarni A, Alves F, Schröter M.   +3 more
europepmc   +1 more source

Short‐Term Multi‐Horizon Line Loss Rate Forecasting of a Distribution Network Using Attention‐GCN‐LSTM

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Accurately predicting line loss rates is crucial for effective management in distribution networks, particularly for short‐term multihorizon forecasts ranging from 1 hour to 1 week. In this study, we propose attention‐GCN–LSTM, a novel method that integrates graph convolutional networks (GCN), long short‐term memory (LSTM) and a three‐level ...
Jie Liu, Yijia Cao, Yong Li, Yixiu Guo, Wei Deng   +4 more
wiley   +1 more source

Research on the sports training effect based on GABP neural network and artificial intelligence. [PDF]

Sci Rep
Li L, Hao A.
europepmc   +1 more source

Multitype Game Optimisation: A Two‐Stage Fine‐Tuning Framework for Multi‑Game Optimisation With Large Language Models

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Large language models (LLMs) have made remarkable advances in natural language processing, demonstrating great potential in modelling structured sequences. However, adapting these capabilities to machine gaming tasks such as Go remains challenging due to limitations in strategy generalisation and optimisation efficiency.
Xiali Li, Jingshi Gu, Feifan He, Yang Xiao, Yuanli Jia, Ping Lan   +5 more
wiley   +1 more source

Enhanced backpropagation neural network accuracy through an improved genetic algorithm for tourist flow prediction in an ecological village. [PDF]

Sci Rep
Chen X, Wong CUI, Zhang H, Song Z.
europepmc   +1 more source

Assessment of off-road agricultural traction in situ using large scale machine learning and neurocomputing models. [PDF]

Sci Rep
Mwiti F, Gitau A, Mbuge D, Njoroge R, Antille DL, Khatti J.   +5 more
europepmc   +1 more source

Applying the maximum entropy principle to neural networks enhances multi‐species distribution models

Methods in Ecology and Evolution, EarlyView.
Abstract The increasing volume of presence‐only (PO) data generated by citizen science initiatives has greatly expanded biodiversity databases, but the statistical use of these data in species distribution models (SDMs) remains limited by strong sampling biases and the absence of reliable absence information.
Maxime Ryckewaert, Diego Marcos, Christophe Botella, Maximilien Servajean, Pierre Bonnet, Alexis Joly   +5 more
wiley   +1 more source

Astrocyte-gated multi-timescale plasticity for online continual learning in deep spiking neural networks. [PDF]

Front Neurosci
Dong Z, He W.
europepmc   +1 more source

Multi‐barcoding‐based species identification using a hierarchical attention network with staged curriculum learning

Methods in Ecology and Evolution, EarlyView.
Abstract DNA barcode‐based species identification has become pivotal in biodiversity research. Current barcoding‐based deep learning methods have advantages in species identification but exhibit significant limitations. By using COI barcoding alone, previous studies were unable to fully capture species identification features. Prior methods showed that
Bin Ye, Junfeng Xia, Xia Wan, Min Wu, Satoshi Chiba   +4 more
wiley   +1 more source