tag:blogger.com,1999:blog-3211409948956809184.comments2024-03-10T21:59:57.367-07:00Large Scale Machine Learning and Other AnimalsDanny Bicksonhttp://www.blogger.com/profile/01517237836051035400noreply@blogger.comBlogger696125tag:blogger.com,1999:blog-3211409948956809184.post-1305340271299363092019-01-10T00:09:37.672-08:002019-01-10T00:09:37.672-08:00Thanks for sharing that such good informationThanks for sharing that such good informationMindtechAffiliateshttps://www.blogger.com/profile/10089740445774896310noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-9012525469451770342017-10-21T09:42:33.414-07:002017-10-21T09:42:33.414-07:00If your edges are not binary (0 or 1) you may have...If your edges are not binary (0 or 1) you may have values outside the range.Danny Bicksonhttps://www.blogger.com/profile/01517237836051035400noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-1729227963515532272017-10-15T21:13:49.299-07:002017-10-15T21:13:49.299-07:00Hi Danny,
I am a little bit confused about the co...Hi Danny,<br /><br />I am a little bit confused about the cosine similarity choice. <br /><br />According to the command line argument, "FOR itemcf2: --distance=XX, 3 = PEARSON, 4=COSINE, " itemcf2: --distance=4 means cosine similarity, but in the reference page, cosine distance are in itemcf, not in itemcf2. <br /><br />I tried with itemcf2, --distance=4 command, which give me similarity value greater than 1, I assume the cosine similarity value should between -1 and 1, right?<br /><br />Could you help me figure out which --distance index should I choose?<br /><br />Thanks,<br />FenAnonymoushttps://www.blogger.com/profile/11106529787820827199noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-10995868125268561302017-05-25T03:12:44.964-07:002017-05-25T03:12:44.964-07:00Thank you, very interesting. I don't think the...Thank you, very interesting. I don't think the big players are particularly a problem, people looking for pipeline.io-style solutions are trying to avoid the big player lock trap.<br /><br />Chris mentions a list with 20 names: do you know what some names on that list might be, besides those you mention?Mario Riverahttps://www.blogger.com/profile/10835086690809997056noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-27995086006322534072017-02-10T23:47:15.556-08:002017-02-10T23:47:15.556-08:00i am getting this error when i try to configure......i am getting this error when i try to configure...<br /><br />configure: error: cannot find any BLAS library, which is required by LAPACK.<br />You can override this error by using "--without-blas" option, but the<br />functionality of the IT++ library will be limited. You have been warned!<br /> please helpMKhttps://www.blogger.com/profile/10814405494007047650noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-46218306597766490282017-01-26T09:40:42.293-08:002017-01-26T09:40:42.293-08:00Thanks for the mention, Danny! Love your work.
H...Thanks for the mention, Danny! Love your work.<br /><br />Here's an updated video, btw: https://youtu.be/swiPWUxBvSc<br /><br />Here's the jupyter notebook that powers the entire demo: https://github.com/fluxcapacitor/pipeline/blob/master/jupyterhub.ml/notebooks/Conferences/StartupML/Jan-20-2017/SparkMLTensorflowAI-HybridCloud-ContinuousDeployment.ipynb<br /><br />Thanks again!Anonymoushttps://www.blogger.com/profile/15260914187076936161noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-67542261260309424232014-07-26T11:44:23.042-07:002014-07-26T11:44:23.042-07:00I recommend trying out GraphLab Create: http://gra...I recommend trying out GraphLab Create: http://graphlab.com/products/create/overview.html it will be easier to set this contest with Graphlab Create.<br /><br />The "\" tells the linux shell to ignore the special meaning of ":" the filename should be something:infoDanny Bicksonhttps://www.blogger.com/profile/01517237836051035400noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-63381300807049772432014-07-26T09:44:55.056-07:002014-07-26T09:44:55.056-07:00Hi Danny,
very impressive work!
But when I try to...Hi Danny, <br />very impressive work!<br />But when I try to create the file yelp_training_set_review.csv\:info, neither windows nor linux allow me to create a file with the symbol \ and :.<br />What should I do?<br /><br />BenAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-75235762829703781552014-07-20T07:54:39.386-07:002014-07-20T07:54:39.386-07:00Great find! I just merged your pull request. Much ...Great find! I just merged your pull request. Much appreciated! Danny Bicksonhttps://www.blogger.com/profile/01517237836051035400noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-8103771891423376182014-07-20T04:32:48.935-07:002014-07-20T04:32:48.935-07:00Hi Danny, I looked into gensgd.cpp to find out the...Hi Danny, I looked into gensgd.cpp to find out the difference of RMSE. It turned out that step3 gets gensgd_rate multiplied 2 times instead of 1 for a step. Now it works. This seems to date from 2 commits made on oct 4 and 10 in 2013. I made a pull request. Regards, XavierAnonymoushttps://www.blogger.com/profile/15231754595069202605noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-83992400651354488682014-07-19T15:24:08.706-07:002014-07-19T15:24:08.706-07:00p.s.
I will be happy to setup up a phone call to d...p.s.<br />I will be happy to setup up a phone call to discuss your problem and give some advice regarding Graphlab Create evaluation.Danny Bicksonhttps://www.blogger.com/profile/01517237836051035400noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-55557780538418185912014-07-19T15:22:36.768-07:002014-07-19T15:22:36.768-07:00Our project has open source foundations and you ca...Our project has open source foundations and you can always stick to the open source if you like. GraphLab Create, while not open source, is still free in the foreseeable future. Fine tuning the open source directly is more difficult. I am now traveling, I will be happy to take a look at the example in a few days - if you don't mind please post a question at our user forum: http://forum.graphlab.com so I could keep track of the issue and not forget.Danny Bicksonhttps://www.blogger.com/profile/01517237836051035400noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-85169923030556077282014-07-19T15:02:07.847-07:002014-07-19T15:02:07.847-07:00Hi Danny,
Thanks for your feedback. GraphLab Creat...Hi Danny,<br />Thanks for your feedback. GraphLab Create seems great but seems risky to me: I went into terms & conditions and read "We grant you a limited, revocable license". I am currently testing different solutions and it seems hard to know what is the future of such an option considering t&c.Xaviernoreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-51120355331742722602014-07-19T13:44:07.769-07:002014-07-19T13:44:07.769-07:00Hi Xavier,
We have re-implmentated this code as p...Hi Xavier, <br />We have re-implmentated this code as part of GraphLab Create. You are highly encouraged to try it out - it is free and it gets to much better results. Send me an email and I will send you the ipython notebook to reproduce the exact same experiment in GLC.Danny Bicksonhttps://www.blogger.com/profile/01517237836051035400noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-52618426275525292442014-07-19T09:29:32.273-07:002014-07-19T09:29:32.273-07:00Hello, Great thanks for this post. I was able to r...Hello, Great thanks for this post. I was able to run all of the different samples but I get an RMSE far higher than expected even after many iterations. <br /><br />For the exemple which should lead to 2 minutes RMSE, I get an RMSE of 32 minutes after 19 iterations.<br /><br />I run an Ubuntu, could it be a library issue or setup ?<br /><br />Thanks Xaviernoreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-19002646770589582522014-07-11T07:35:43.719-07:002014-07-11T07:35:43.719-07:00YES.YES.Danny Bicksonhttps://www.blogger.com/profile/01517237836051035400noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-18418653672478733182014-07-03T08:51:24.860-07:002014-07-03T08:51:24.860-07:00Hi, will the talks from this conference be availab...Hi, will the talks from this conference be available online?Naveenhttps://www.blogger.com/profile/17093217100573285086noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-69093559893334536222014-07-03T02:47:17.056-07:002014-07-03T02:47:17.056-07:00is it possible to use GraphLab in java?
is it poss...is it possible to use GraphLab in java?<br />is it possible to use graphlab for web classification?ANIL SHAH ( TECHNICAL ANALYST )https://www.blogger.com/profile/09724336175416748838noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-28382589563349116772014-07-02T07:38:32.375-07:002014-07-02T07:38:32.375-07:00Thanks. In order to low RMSE for the test sets, I ...Thanks. In order to low RMSE for the test sets, I am tuning rbm_alpha, rbm_beta, D (not sure if it is necessary to tune D). Is there any other parameters I need to tune? Thanks.xwhttps://www.blogger.com/profile/02009956436501209212noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-91726080656579598402014-07-01T22:21:20.699-07:002014-07-01T22:21:20.699-07:00D is always the latent feature vector width (as in...D is always the latent feature vector width (as in all methods).<br />multiplicative step decrement is how much you decrease the SGD step size. The default is 0.9, namely you multiply by 0.9 the step size after each iteration.Danny Bicksonhttps://www.blogger.com/profile/01517237836051035400noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-20773089186751933902014-07-01T12:21:07.155-07:002014-07-01T12:21:07.155-07:00Dear Danny,
About rbm, what is the parameter D? ho...Dear Danny,<br />About rbm, what is the parameter D? how to give a value to D? what does the rbm_mult_step_dec mean? Thanks!xwhttps://www.blogger.com/profile/02009956436501209212noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-20268096880339179352014-07-01T08:53:11.452-07:002014-07-01T08:53:11.452-07:00This comment has been removed by the author.xwhttps://www.blogger.com/profile/02009956436501209212noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-80948292227702983922014-06-30T21:31:55.141-07:002014-06-30T21:31:55.141-07:00We would love a code contribution!We would love a code contribution!Danny Bicksonhttps://www.blogger.com/profile/01517237836051035400noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-83897855717854118732014-06-30T14:19:14.096-07:002014-06-30T14:19:14.096-07:00BigCLAM is indeed quite interesting, I am in the p...BigCLAM is indeed quite interesting, I am in the process of implementing it in GraphChi right now by building upon your SGD code.Unknownhttps://www.blogger.com/profile/06011564627713103714noreply@blogger.comtag:blogger.com,1999:blog-3211409948956809184.post-21203335655695097062014-06-07T09:59:11.957-07:002014-06-07T09:59:11.957-07:00Hi,
In graphchi we have item based methods. In Gr...Hi, <br />In graphchi we have item based methods. In GraphLab Create we are working on k-NN methods. Once it is ready we will announce on our website.Danny Bicksonhttps://www.blogger.com/profile/01517237836051035400noreply@blogger.com