IMO, 1. slide 7 is good. I think this slide (comparison with spark, giraph etc.) should be emphasized. 2. How about refer the fact that the domain of problems that can be solved by MapReduce computation is equal to that of BSP? Add to this, BSP computation model is more flexible and easy to represent[1, 2, 3]. This point will be useful when you make a explanation on usefulness of HAMA's computation model.
Thanks. 1. arxiv.org/pdf/1101.1902.pdf 2. arxiv.org/pdf/1004.4708.pdf 3. arxiv.org/pdf/1203.2081.pdf On Mon, Sep 1, 2014 at 6:11 PM, Edward J. Yoon <[email protected]> wrote: > Hi, > > I'll give a finale talk at Samsung Open Source Conference 2014 (Sep > 17). If you have some time, Please review and comment on my slides[1]. > > Thanks. > > 1. > https://docs.google.com/presentation/d/1QAg7AC9Atz3gXHuBKSf_cmoG0u1qdmfsMTVjOeTEbRg/edit?usp=sharing > > -- > Best Regards, Edward J. Yoon > CEO at DataSayer Co., Ltd. > -- *Dongjin Lee* *So interested in massive-scale machine learning.facebook: www.facebook.com/dongjin.lee.kr <http://www.facebook.com/dongjin.lee.kr>linkedin: kr.linkedin.com/in/dongjinleekr <http://kr.linkedin.com/in/dongjinleekr>github: <http://goog_969573159>github.com/dongjinleekr <http://github.com/dongjinleekr>twitter: www.twitter.com/dongjinleekr <http://www.twitter.com/dongjinleekr>*
