Abstract: Simultaneous tensor communication can effectively improve the scalability of distributed deep learning on large clusters. However, a fixed number of tensor blocks communicated concurrently ...

This project is an educational and research-oriented implementation that benchmarks and compares different metaheuristic algorithms for solving VRPTW problems. The VRPTW is a classic NP-hard ...

Abstract: Sensory data has been widely used for human activity recognition (HAR), where sliding window (SW) is one of the typical methods to segment continuous signals. Most existing HAR methods ...

Detail from a figure in the study shows brainstem bundle regions of interest In three different cross-sections of a brain, as automatically determined by BSBT (top row) vs. a "ground-truth" method.