we talked about - MapR's inclusion of Mahout in their distro - Time series and data mining, Keogh's work, his work with SAX - Grant prodded everyone to contribute more code - Ted educated us on a number of topics, I lost count =) - ideas around MR2 and Mahout, the need for a workflow that uses both MR and other execution frameworks - the concept of a version of Pig that compiles into the aforementioned workflow and uses the best execution framework, MR or not, as it sees fit - some talk about the rise of recommendation engines - Ted talked a bit about SGD and its incredible performance in serial mode, compared to other parallel methods such as naive bayes - talked a bit about the coming mahout book
... and more? someone else chime in here... On Fri, May 27, 2011 at 5:01 AM, Isabel Drost <[email protected]> wrote: > On 13.05.2011 Grant Ingersoll wrote: >> Anyone game? > > For all those of us currently not in SFO: Would be great if anyone could > write a > brief summary of the meetup (beer counters included if you like ;) > > > Isabel > -- Twitter: @jpatanooga Solution Architect @ Cloudera hadoop: http://www.cloudera.com blog: http://jpatterson.floe.tv
