Zobrazeno 1 - 10
of 121
pro vyhledávání: '"Aune, Erlend"'
State-of-the-art approaches in time series generation (TSG), such as TimeVQVAE, utilize vector quantization-based tokenization to effectively model complex distributions of time series. These approaches first learn to transform time series into a seq
Externí odkaz:
http://arxiv.org/abs/2408.16613
Publikováno v:
Pattern Recognition, 156, 110826 (2024)
We present a novel time series anomaly detection method that achieves excellent detection accuracy while offering a superior level of explainability. Our proposed method, TimeVQVAE-AD, leverages masked generative modeling adapted from the cutting-edg
Externí odkaz:
http://arxiv.org/abs/2311.12550
Creating accurate and geologically realistic reservoir facies based on limited measurements is crucial for field development and reservoir management, especially in the oil and gas sector. Traditional two-point geostatistics, while foundational, ofte
Externí odkaz:
http://arxiv.org/abs/2311.01968
This paper presents a novel sampling scheme for masked non-autoregressive generative modeling. We identify the limitations of TimeVQVAE, MaskGIT, and Token-Critic in their sampling processes, and propose Enhanced Sampling Scheme (ESS) to overcome the
Externí odkaz:
http://arxiv.org/abs/2309.07945
Time series generation (TSG) studies have mainly focused on the use of Generative Adversarial Networks (GANs) combined with recurrent neural network (RNN) variants. However, the fundamental limitations and challenges of training GANs still remain. In
Externí odkaz:
http://arxiv.org/abs/2303.04743
Time series forecasting is an important problem, with many real world applications. Ensembles of deep neural networks have recently achieved impressive forecasting accuracy, but such large ensembles are impractical in many real world settings. Transf
Externí odkaz:
http://arxiv.org/abs/2208.14236
One of the latest self-supervised learning (SSL) methods, VICReg, showed a great performance both in the linear evaluation and the fine-tuning evaluation. However, VICReg is proposed in computer vision and it learns by pulling representations of rand
Externí odkaz:
http://arxiv.org/abs/2204.02697
Publikováno v:
In Pattern Recognition December 2024 156
Autor:
Lee, Daesoo, Aune, Erlend
Self-supervised learning (SSL) has had great success in both computer vision. Most of the current mainstream computer vision SSL frameworks are based on Siamese network architecture. These approaches often rely on cleverly crafted loss functions and
Externí odkaz:
http://arxiv.org/abs/2109.00783
One of the major challenges in training deep architectures for predictive tasks is the scarcity and cost of labeled training data. Active Learning (AL) is one way of addressing this challenge. In stream-based AL, observations are continuously made av
Externí odkaz:
http://arxiv.org/abs/1909.01757