Results 1 to 10 of about 24,937,001 (335)
Are Transformers Effective for Time Series Forecasting? [PDF]
AAAI Conference on Artificial Intelligence, 2022 Recently, there has been a surge of Transformer-based solutions for the long-term time series forecasting (LTSF) task. Despite the growing performance over the past few years, we question the validity of this line of research in this work.
Ailing Zeng +3 more
semanticscholar +1 more source
iTransformer: Inverted Transformers Are Effective for Time Series Forecasting [PDF]
International Conference on Learning Representations, 2023 The recent boom of linear forecasting models questions the ongoing passion for architectural modifications of Transformer-based forecasters. These forecasters leverage Transformers to model the global dependencies over temporal tokens of time series ...
Yong Liu +6 more
semanticscholar +1 more source
A Simple and Effective Pruning Approach for Large Language Models [PDF]
International Conference on Learning Representations, 2023 As their size increases, Large Languages Models (LLMs) are natural candidates for network pruning methods: approaches that drop a subset of network weights while striving to preserve performance.
Mingjie Sun +3 more
semanticscholar +1 more source
The Flan Collection: Designing Data and Methods for Effective Instruction Tuning [PDF]
International Conference on Machine Learning, 2023 We study the design decisions of publicly available instruction tuning methods, and break down the development of Flan 2022 (Chung et al., 2022). Through careful ablation studies on the Flan Collection of tasks and methods, we tease apart the effect of ...
S. Longpre +10 more
semanticscholar +1 more source
Learning A Sparse Transformer Network for Effective Image Deraining [PDF]
Computer Vision and Pattern Recognition, 2023 Transformers-based methods have achieved significant performance in image deraining as they can model the non-local information which is vital for high-quality image reconstruction.
Xiang Chen +3 more
semanticscholar +1 more source
Geofluids, 2023 This study is focused on the problem that with the increase of coal seam mining depth, it is difficult to continuously replace mining due to complex roadway layout and unreasonable stope layout.
Wenbao Shi +4 more
doaj +1 more source
Effective Approaches to Attention-based Neural Machine Translation [PDF]
Conference on Empirical Methods in Natural Language Processing, 2015 An attentional mechanism has lately been used to improve neural machine translation (NMT) by selectively focusing on parts of the source sentence during translation.
Thang Luong +2 more
semanticscholar +1 more source
Geofluids, 2022 The development of natural fracture will lead to lost circulation, which will be likely to cause economic losses and reduce drilling efficiency. In order to solve this problem, an oil-based pressure-bearing foam gel plugging agent for fractured shale was
Daqi Li +5 more
doaj +1 more source
Calculation Model of Relative Permeability in Tight Sandstone Gas Reservoir with Stress Sensitivity
Geofluids, 2021 During the development of tight gas reservoir, the irreducible water saturation, rock permeability, and relative permeability change with formation pressure, which has a significant impact on well production.
Jin Yan +4 more
doaj +1 more source
The Effectiveness of Website as a Mathematics Learning Media During the Online Learning Period
Edumatica: Jurnal Pendidikan Matematika, 2021 The Covid-19 pandemic caused learning activities to immediately stop and be diverted online. There are many obstacles faced by teachers and students.
Weni Dwi Susanti, Suripah Suripah
doaj +1 more source