Our second R&D Report, Probabilistic Methods for Realtime Streams, has gone out! In this report, we explored probabilistic algorithms for machine learning on potentially large realtime streams of data with efficient CPU and memory usage.
Our prototype demonstrated these algorithms running on large amounts of social conversation data. More on that soon.
More from the Blog
Mar 31 2015
The Hoff stopped by Fast Forward Labs!
Apr 6 2015
by — It’s restyled blog day here at Fast Forward Labs! Having wrapped up our second report, I (Grant, Fast Forward Labs designer-dev) am now spending some time putting our web presence in order. The real big piece of that is a revamped Fast Forward website, which should be out next week, but as a warm-up today I worked on getting our blog into shape. I wanted to keep things clean ...
Sep 17 2018
Deep learning has provided extraordinary advances in problem spaces that are poorly solved by other approaches. This success is due to several key departures from traditional machine learning that allow it to excel when applied to unstructured data. Today, deep learning models can play games, detect cancer, talk to humans, and drive cars. But the differences that make deep learning power...