IEEE

Block Convolution: Toward Memory-Efficient Inference of Large-Scale CNNs on FPGA

Abstract: Deep convolutional neural networks have achieved remarkable progress in recent years. However, the large volume of intermediate results generated during inference poses a significant ...
IEEE

Temporal Convolution-Based Long-Short Term Memory Network With Attention Mechanism for Remaining Useful Life Prediction

Abstract: Predictive maintenance (PdM) is useful for engineers to schedule maintenance flexibly, to operate equipment efficiently, and also to avoid unexpected downtime. Remaining useful life (RUL) ...
GitHub

Content-Adaptive Non-Local Convolution for Remote Sensing Pansharpening

Abstract: Currently, machine learning-based methods for remote sensing pansharpening have progressed rapidly. However, existing pansharpening methods often do not fully exploit differentiating ...
National Bureau of Economic Research

Zero-sum Thinking and the Roots of US Political Differences

We investigate the origins and implications of zero-sum thinking: the belief that gains for one individual or group tend to come at the cost of others. Using a new survey of 20,400 U.S. residents, we ...
GitHub

ModernTCN (ICLR 2024 Spotlight)

Donghao Luo and Xue Wang. ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis. In International Conference on Learning Representations, 2024. [Our paper in OpenReview]. We ...