Deep Learning

SPARC, a transformer-based foundation model trained on more than 100 million routinely collected longitudinal clinical measurements from 224,047 patients with cancer, predicts treatment-related adverse events and generalizes to external centers.

We apply model compression techniques such as pruning and quantization to deep learning image compression models and find that pruning affects different components of these models differently.

We propose a 2-D CNN-LSTM deep learning model that uses a MIMO radar to accurately detect, count, and classify passengers in five-seater vehicles, achieving over 95% accuracy in detecting unattended infants/children, 89% accuracy in counting passengers and identifying their seats, and 74% accuracy in classifying passengers, demonstrating its applicability in any five-seater vehicle.

In the past decade, there has been an increasing demand for in-vehicle safety sensors. In this paper, we use a multi-input multi-output …

Based on the idea of patient similarity networks, we extended a graph convolutional network framework to classify clinical outcomes of cancer patients.