Researchers from the Massachusetts Institute of Technology have developed a machine learning algorithm in which distributed agents collect data and analyze it independently. Pairs of agents, such as robots passing each other in the hall, then exchange analyses. In experiments , the researchers’ distributed algorithm outperformed a standard algorithm that works on data aggregated at a single location. The algorithm has implications for big data because it could allow distributed servers to combine the results of their data analyses without aggregating the data at a central location.
Source: MIT
