Stream Computation

research

About This Project

This project is meant to serve as an adaptation of conventional machine learning data processing techniques, most notably batch processing, for continuous, real-time streams of data.

Asymptotically, the latency in data processing grows quickly as the batches of data become more and more fine grained.

The goal of this project is to design a graph-based framework to aid in the conversion of the many batch processing algorithms to data streams, in a way that's amenable to multiprocessing and parallelism on distributed computing systems.

Project Members

Stream Computation

currently no documents uploaded for this project

<< Back to Portfolio