Related papers: TUNet: A Block-online Bandwidth Extension Model ba…

Learning representations that accurately capture long-range dependencies in sequential inputs -- including text, audio, and genomic data -- is a key problem in deep learning. Feed-forward convolutional models capture only feature…

Time series data, characterized by its intrinsic long and short-range dependencies, poses a unique challenge across analytical applications. While Transformer-based models excel at capturing long-range dependencies, they face limitations in…

Traction force microscopy (TFM) is a widely used technique for quantifying the forces that cells exert on their surrounding extracellular matrix. Although deep learning methods have recently been applied to TFM data analysis, several…

The integration of terahertz communications and ultra-massive multiple-input multiple-output (UM-MIMO) systems in 6G networks is motivated by their ability to enable unprecedented data rates, mitigate spectrum congestion, and enhance…

Recent studies have shown that deep learning models such as RNNs and Transformers have brought significant performance gains for long-term forecasting of time series because they effectively utilize historical information. We found,…

Long-term time series forecasting is a vital task and has a wide range of real applications. Recent methods focus on capturing the underlying patterns from one single domain (e.g. the time domain or the frequency domain), and have not taken…

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…

We show that Transformer encoder architectures can be sped up, with limited accuracy costs, by replacing the self-attention sublayers with simple linear transformations that "mix" input tokens. These linear mixers, along with standard…

We propose a deep learning based novel prediction framework for enhanced bandwidth reduction in motion transfer enabled video applications such as video conferencing, virtual reality gaming and privacy preservation for patient health…

The UNet-enhanced Fourier Neural Operator (UFNO) extends the Fourier Neural Operator (FNO) by incorporating a parallel UNet pathway, enabling the retention of both high- and low-frequency components. While UFNO improves predictive accuracy…

This paper proposes a model that integrates sub-band processing and deep filtering to fully exploit information from the target time-frequency (TF) bin and its surrounding TF bins for single-channel speech enhancement. The sub-band module…

Recent research has challenged the necessity of complex deep learning architectures for time series forecasting, demonstrating that simple linear models can often outperform sophisticated approaches. Building upon this insight, we introduce…

We consider small-data, large-scale decision problems in which a firm must make many operational decisions simultaneously (e.g., across a large product portfolio) while observing only a few, potentially noisy, data points per instance.…

Rapid advancements in GPU computational power has outpaced memory capacity and bandwidth growth, creating bottlenecks in Large Language Model (LLM) inference. Post-training quantization is the leading method for addressing memory-related…

While numerous forecasters have been proposed using different network architectures, the Transformer-based models have state-of-the-art performance in time series forecasting. However, forecasters based on Transformers are still suffering…

This study presents a novel fault diagnosis model for urban rail transit systems based on Wavelet Transform Residual Neural Network (WT-ResNet). The model integrates the advantages of wavelet transform for feature extraction and ResNet for…

Time series prediction is a prevalent issue across various disciplines, such as meteorology, traffic surveillance, investment, and energy production and consumption. Many statistical and machine-learning strategies have been developed to…

Recently, Transformer-base models have made significant progress in the field of time series prediction which have achieved good results and become baseline models beyond Dlinear. The paper proposes an U-Net time series prediction model…

More transformer blocks with residual connections have recently achieved impressive results on various tasks. To achieve better performance with fewer trainable parameters, recent methods are proposed to go shallower by parameter sharing or…

This paper proposes a delayed subband LSTM network for online monaural (single-channel) speech enhancement. The proposed method is developed in the short time Fourier transform (STFT) domain. Online processing requires frame-by-frame signal…