Although the quest for more accurate solutions is pushing deep learning research towards
larger and more complex algorithms, edge devices demand efficient inference and therefore …

A common pain point in differentially private machine learning is the significant runtime
overhead incurred when executing Differentially Private Stochastic Gradient Descent …

Deep learning (DL) research yields accuracy and product improvements from both model
architecture changes and scale: larger data sets and models, and more computation. For …

Recognition of building group patterns is of great significance for understanding and
modeling the urban space. However, many current methods cannot fully utilize spatial …

Predicting crop yields, and especially anomalously low yields, is of special importance for
food insecure countries. In this study, we investigate a flexible deep learning approach to …

Quasars that exhibit blueshifted, broad absorption lines (BAL QSOs) are an important probe
of black hole feedback on galaxy evolution. Yet the presence of BALs is also a complication …

This paper introduces a sequential approximate optimization method that combines the finite
element method (FEM), dynamic differential evolution (DDE), and artificial neural network …

There is a growing interest in enhancing compiler optimizations with ML models, yet
interactions between compilers and ML frameworks remain challenging. Some optimizations …

GPUs are increasingly being used used to speed up Python applications in the scientific
computing and machine learning domains. Currently, the two common approaches to …

Convolutional neural networks (CNNs) and deep learning are powerful and robust tools for
ecological applications, and are particularly suited for image data. Image segmentation (the …