2

This work describes a multi-firearm, multi-orientation, time-synchronized audio dataset collected in a semi-controlled real-world setting, which is ideal for gunshots detection and discharging firearm recognition tasks.

In this work we present a prototype ML-based framework for flood warning and flood peak prediction based on catchment characteristics and precipitation profiles. Based on this framework we analyze a host of findings across 18 distinct hydroclimatic regions across the contiguous US.

We show a Talagrand-type concentration inequality for Multi-Task Learning (MTL), with which we establish sharp excess risk bounds for …

In machine learning, the notion of multi-objective model selection (MOMS) refers to the problem of identifying the set of …