How I can contribute to it? It is already implemented but maybe not in Mahout.
On Wed, Oct 5, 2011 at 8:02 PM, Lance Norskog <[email protected]> wrote: > I stand (privately) corrected: > > ---------------------------------------- > Actually, on-line algorithms are ones that use constant memory and constant > time per input record. This may mean that they can run on demand, or not. > > What is most important is that run-time will be linear or better in input > size and if it succeeds on small input, it will succeed on large input > (eventually). > > http://en.wikipedia.org/wiki/Online_algorithm > ------------------------ > > If you wish to contribute something really cool to Mahout, I recently found > this online implementation of Singular Value Decomposition (SVD). It updates > the SVD incrementally, and is used in a recommender. This algorithm has also > been used to track shapes in real-time in computer vision. > > http://www.merl.com/publications/TR2003-014/ > > > On Wed, Oct 5, 2011 at 3:51 PM, Lance Norskog <[email protected]> wrote: > >> There are many "online" algorithms which do not use Hadoop or map/reduce. >> Online means that the code runs on demand; Hadoop jobs create large >> datasets. Online algorithms may use the output of Hadoop, or process input >> data directly. >> >> Try learning an area of the online algorithms like recommender systems or >> classifiers- you will learn much more quickly. You will find that Hadoop is >> an amazing time-waster. >> >> Lance >> >> >> On Wed, Oct 5, 2011 at 11:35 AM, Isabel Drost <[email protected]> wrote: >> >>> >>> First of all welcome also from my side. >>> >>> On 05.10.2011 Apurv Verma wrote: >>> > I am interested in becoming a contributor to Mahout. >>> >>> Actually we have a "How to contribute page" on our wiki that might help >>> you: >>> >>> https://cwiki.apache.org/MAHOUT/how-to-contribute.html >>> >>> I guess the general take away is to start using Mahout for your own >>> projects. As >>> with any software you use sooner or later you will find stuff that bothers >>> you: >>> Missing documentation, extensions you need to make here and there, sutle >>> bugs. >>> >>> >>> > But unfortunately I have not had any course in Machine Learning still. >>> I am >>> > having a course in Artificial Intelligence this semester. >>> >>> While it is certainly a great help to have some machine learning >>> background, you >>> do not need a PhD to start contributing to Mahout. Any infrastructure >>> improvements that do not change the inner algorithms but make it easier to >>> integrate Mahout and re-use it are highly welcome. >>> >>> >>> > I am also *not* conversant with hadoop and mapreduce though I have heard >>> of >>> > it and have long wanted to learn it. Can someone please guide me (mentor >>> > informally) so that I may get a sense and direction and I am able to >>> > develop the skills set required to contribute to this project within the >>> > next 6 months. >>> >>> You have taken a very good first step by contacting the mailing list. Try >>> to >>> figure out an area that you would like to use Mahout for, start working in >>> that >>> direction, if you come across any questions that cannot be answered by a >>> trivial >>> search in the mailing list archives don't be shy to ask on list. When >>> getting >>> more proficient answer questions other new-comers may have, start >>> reviewing >>> patches and maybe even contribute your own improvements. >>> >>> Isabel >>> >> >> >> >> -- >> Lance Norskog >> [email protected] >> >> > > > -- > Lance Norskog > [email protected] >
