However, the commonly used mini-batch stochastic gradient descent (SGD) training paradigm treats each sample equally, resulting in massive computational waste on samples that are easily identifiable.

A few weeks ago we featured a project from [Dan], a work-in-progress in which he was attaching an EMF 2018 electronic conference badge to a rotary phone. At the time we looked forward to his ...

Over the last year, the production of homebrew electronic badges for conferences has exploded. This is badgelife — the creation of custom hardware, a trial by fire of manufacturing, and a ...