Paper
LLMs & Texto
Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting
Quantum-inspired recurrent models using gated QKAN-FWPs demonstrate superior forecasting accuracy with reduced computational requirements compared to traditional LSTM networks for…
Hugging Face · Daily Papers
·Kuo-Chung Peng, Jiun-Cheng Jiang
·
·▲ 1 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Kuo-Chung Peng, Jiun-Cheng Jiang, Chun-Hua Lin, Tai-Yue Li, Nan-Yow Chen, Samuel Yen-Chi Chen
- 1 upvotes da comunidade
- Temas: traffic matrices, quantum-inspired recurrent models, gated quantum-inspired Kolmogorov-Arnold network fast-weight programmers, QKAN-FWPs, multi-step forecasting, origin-destination matrix
Resumo
Resumo original (em inglês), extraído do paper:
Quantum-inspired recurrent models using gated QKAN-FWPs demonstrate superior forecasting accuracy with reduced computational requirements compared to traditional LSTM networks for traffic matrix prediction.Onde ler
// relacionados
Leia também
Blog
O complicado problema do Claude Code com a China envolve proibições dos dois lados do Pacífico
Blog
AI Security Institute do Reino Unido descobre que benchmarks padrão subestimam sistematicamente o que agentes de IA realmente conseguem fazer
Dataset
ByteDance-Seed/EdgeBench
Blog