Let's use H2O then. On Fri, Jun 19, 2015 at 4:31 PM, Thushan Ganegedara <thu...@gmail.com> wrote:
> Yes, the results look very promising. The deep networks are performing > very well. > > On Fri, Jun 19, 2015 at 7:59 PM, Srinath Perera <srin...@wso2.com> wrote: > >> We should/can use H2O if it is better. >> >> On Fri, Jun 19, 2015 at 3:20 PM, Thushan Ganegedara <thu...@gmail.com> >> wrote: >> >>> Hi all, >>> >>> I ran a simple example for MNIST dataset on H2O-Flow >>> >>> These are the results I obtained. Seems like a promising option. >>> >>> >>> On Fri, Jun 19, 2015 at 2:11 PM, Thushan Ganegedara <thu...@gmail.com> >>> wrote: >>> >>>> Hi, >>>> >>>> H2O seems to be a very reliable option. They have quite a few strong >>>> testimonials too. And seems to be well documented too. Should I try to run >>>> few tests with H2O API? >>>> >>>> On Fri, Jun 19, 2015 at 12:17 PM, Srinath Perera <srin...@wso2.com> >>>> wrote: >>>> >>>>> Have we look at h2o's DL impl? >>>>> >>>>> e.g. >>>>> http://www.businesswire.com/news/home/20150616006734/en/H2O.ai-Showcases-Power-Deep-Learning-GBM-Spark >>>>> >>>>> On Thu, Jun 18, 2015 at 7:43 AM, Thushan Ganegedara <thu...@gmail.com> >>>>> wrote: >>>>> >>>>>> Hi, >>>>>> >>>>>> Yes, that sounds good. I will start working on UI aspects while >>>>>> waiting for them to release fixes. If they release fixes while working on >>>>>> the UI it should be fine. Otherwise, I will start implementing the >>>>>> autoencoder. >>>>>> >>>>>> On Thu, Jun 18, 2015 at 12:04 PM, Srinath Perera <srin...@wso2.com> >>>>>> wrote: >>>>>> >>>>>>> Let's work on other parts of the project, for example we can look at >>>>>>> UI to configure Deep learning while waiting for them to do it. However, >>>>>>> fix >>>>>>> takes time, we have to write auto encoder. >>>>>>> >>>>>>> On Thu, Jun 18, 2015 at 7:26 AM, Thushan Ganegedara < >>>>>>> thu...@gmail.com> wrote: >>>>>>> >>>>>>>> Dear all, >>>>>>>> >>>>>>>> I posted about poor accuracy on deeplearning4j google group and >>>>>>>> they replied saying they are aware of this issue ( >>>>>>>> https://groups.google.com/forum/#!topic/deeplearning4j/gRQH8rA9SQI). >>>>>>>> They are currently working on it, to get the tuned examples out soon. >>>>>>>> >>>>>>>> However, from the appearance of their response, deeplearning4j has >>>>>>>> few bugs/issues with gradient calculation after they moved to nd4j. >>>>>>>> >>>>>>>> I can see two options right now, >>>>>>>> >>>>>>>> 1. Wait till the bugs are fixed and tuned examples are out >>>>>>>> 2. Write autoencoder myself, adhering to the coding style they have >>>>>>>> followed. So the example can be easily integrated with deeplearning4j >>>>>>>> after >>>>>>>> a stable version is out. >>>>>>>> >>>>>>>> >>>>>>>> Would highly appreciate your feedback. >>>>>>>> >>>>>>>> On Wed, Jun 17, 2015 at 10:27 AM, Thushan Ganegedara < >>>>>>>> thu...@gmail.com> wrote: >>>>>>>> >>>>>>>>> Hi, >>>>>>>>> >>>>>>>>> I couldn't find any reports on high accuracy on any set of data. >>>>>>>>> The popular datasets seem to be Iris dataset and MNIST dataset. >>>>>>>>> However, >>>>>>>>> their example page on git hub shows several results for different >>>>>>>>> techniques and datasets ( >>>>>>>>> https://github.com/deeplearning4j/dl4j-0.0.3.3-examples). And as >>>>>>>>> it can be seen, the accuracies mentioned are quite low. (However, the >>>>>>>>> developers claim that this is because they have run the examples with >>>>>>>>> less >>>>>>>>> number of nodes and less iterations) >>>>>>>>> >>>>>>>>> >>>>>>>>> >>>>>>>>> On Tue, Jun 16, 2015 at 6:03 PM, Srinath Perera <srin...@wso2.com> >>>>>>>>> wrote: >>>>>>>>> >>>>>>>>>> Are there any other datasets where dl4j suppose to do well? As >>>>>>>>>> long as it does better with *some* datasets, we can go ahead with >>>>>>>>>> those? >>>>>>>>>> >>>>>>>>>> On Tue, Jun 16, 2015 at 9:13 AM, Thushan Ganegedara < >>>>>>>>>> thu...@gmail.com> wrote: >>>>>>>>>> >>>>>>>>>>> Yes, there are few use list (Git hub and google group). I will >>>>>>>>>>> inquire about this in user lists. >>>>>>>>>>> >>>>>>>>>>> Thank you >>>>>>>>>>> >>>>>>>>>>> >>>>>>>>>>> On Tue, Jun 16, 2015 at 12:34 PM, Nirmal Fernando < >>>>>>>>>>> nir...@wso2.com> wrote: >>>>>>>>>>> >>>>>>>>>>>> Thanks Thushan for the update. >>>>>>>>>>>> >>>>>>>>>>>> In addition to you digging into the code, can you also inquire >>>>>>>>>>>> on the poor performance from the DL4J user list (if there's one >>>>>>>>>>>> exist)? >>>>>>>>>>>> >>>>>>>>>>>> On Tue, Jun 16, 2015 at 5:27 AM, Thushan Ganegedara < >>>>>>>>>>>> thu...@gmail.com> wrote: >>>>>>>>>>>> >>>>>>>>>>>>> Dear all, >>>>>>>>>>>>> >>>>>>>>>>>>> Please find the update regarding DL4J testing >>>>>>>>>>>>> >>>>>>>>>>>>> *Poor Accuracy* >>>>>>>>>>>>> I have been testing DL4J extensively with *MNIST and Iris* >>>>>>>>>>>>> datasets (Small and Full). However, I was unable to get a >>>>>>>>>>>>> reasonable >>>>>>>>>>>>> accuracy with DL4J for the aforementioned datasets. The F1-score >>>>>>>>>>>>> was around >>>>>>>>>>>>> 0.02, which is very low. >>>>>>>>>>>>> >>>>>>>>>>>>> I tried with different settings mainly for the following >>>>>>>>>>>>> attributes >>>>>>>>>>>>> >>>>>>>>>>>>> Weight initialization >>>>>>>>>>>>> Gradient Descent >>>>>>>>>>>>> Iterations >>>>>>>>>>>>> Type of units: Autoencoder/RBM >>>>>>>>>>>>> >>>>>>>>>>>>> >>>>>>>>>>>>> But none of the settings gave a reasonable accuracy. >>>>>>>>>>>>> Furthermore, the predicted values for the test data usually >>>>>>>>>>>>> *belong >>>>>>>>>>>>> to 1 or 2 classes *(e.g. when trained on MNIST dataset, the >>>>>>>>>>>>> program predict 0 and 1 only, though there are 10 possible >>>>>>>>>>>>> classes) >>>>>>>>>>>>> >>>>>>>>>>>>> Also there are many reports of *poor accuracy of DL4J.* The >>>>>>>>>>>>> best accuracy I could find reported was around 0.5 F1 score for >>>>>>>>>>>>> MNIST, >>>>>>>>>>>>> which is still very low. (e.g. MNIST can easily reach 0.9+ >>>>>>>>>>>>> accuracy for >>>>>>>>>>>>> even a basic deep network) >>>>>>>>>>>>> >>>>>>>>>>>>> I'm currently trying to delve in to the code for DL4J and >>>>>>>>>>>>> figure out how the learning is done. I'm assuming there are some >>>>>>>>>>>>> faults in >>>>>>>>>>>>> the learning process which causes the algorithm to learn poorly. >>>>>>>>>>>>> >>>>>>>>>>>>> Thank you >>>>>>>>>>>>> >>>>>>>>>>>>> -- >>>>>>>>>>>>> Regards, >>>>>>>>>>>>> >>>>>>>>>>>>> Thushan Ganegedara >>>>>>>>>>>>> School of IT >>>>>>>>>>>>> University of Sydney, Australia >>>>>>>>>>>>> >>>>>>>>>>>> >>>>>>>>>>>> >>>>>>>>>>>> >>>>>>>>>>>> -- >>>>>>>>>>>> >>>>>>>>>>>> Thanks & regards, >>>>>>>>>>>> Nirmal >>>>>>>>>>>> >>>>>>>>>>>> Associate Technical Lead - Data Technologies Team, WSO2 Inc. >>>>>>>>>>>> Mobile: +94715779733 >>>>>>>>>>>> Blog: http://nirmalfdo.blogspot.com/ >>>>>>>>>>>> >>>>>>>>>>>> >>>>>>>>>>>> >>>>>>>>>>> >>>>>>>>>>> >>>>>>>>>>> -- >>>>>>>>>>> Regards, >>>>>>>>>>> >>>>>>>>>>> Thushan Ganegedara >>>>>>>>>>> School of IT >>>>>>>>>>> University of Sydney, Australia >>>>>>>>>>> >>>>>>>>>> >>>>>>>>>> >>>>>>>>>> >>>>>>>>>> -- >>>>>>>>>> ============================ >>>>>>>>>> Blog: http://srinathsview.blogspot.com twitter:@srinath_perera >>>>>>>>>> Site: http://people.apache.org/~hemapani/ >>>>>>>>>> Photos: http://www.flickr.com/photos/hemapani/ >>>>>>>>>> Phone: 0772360902 >>>>>>>>>> >>>>>>>>> >>>>>>>>> >>>>>>>>> >>>>>>>>> -- >>>>>>>>> Regards, >>>>>>>>> >>>>>>>>> Thushan Ganegedara >>>>>>>>> School of IT >>>>>>>>> University of Sydney, Australia >>>>>>>>> >>>>>>>> >>>>>>>> >>>>>>>> >>>>>>>> -- >>>>>>>> Regards, >>>>>>>> >>>>>>>> Thushan Ganegedara >>>>>>>> School of IT >>>>>>>> University of Sydney, Australia >>>>>>>> >>>>>>> >>>>>>> >>>>>>> >>>>>>> -- >>>>>>> ============================ >>>>>>> Blog: http://srinathsview.blogspot.com twitter:@srinath_perera >>>>>>> Site: http://people.apache.org/~hemapani/ >>>>>>> Photos: http://www.flickr.com/photos/hemapani/ >>>>>>> Phone: 0772360902 >>>>>>> >>>>>> >>>>>> >>>>>> >>>>>> -- >>>>>> Regards, >>>>>> >>>>>> Thushan Ganegedara >>>>>> School of IT >>>>>> University of Sydney, Australia >>>>>> >>>>> >>>>> >>>>> >>>>> -- >>>>> ============================ >>>>> Blog: http://srinathsview.blogspot.com twitter:@srinath_perera >>>>> Site: http://people.apache.org/~hemapani/ >>>>> Photos: http://www.flickr.com/photos/hemapani/ >>>>> Phone: 0772360902 >>>>> >>>> >>>> >>>> >>>> -- >>>> Regards, >>>> >>>> Thushan Ganegedara >>>> School of IT >>>> University of Sydney, Australia >>>> >>> >>> >>> >>> -- >>> Regards, >>> >>> Thushan Ganegedara >>> School of IT >>> University of Sydney, Australia >>> >> >> >> >> -- >> ============================ >> Blog: http://srinathsview.blogspot.com twitter:@srinath_perera >> Site: http://people.apache.org/~hemapani/ >> Photos: http://www.flickr.com/photos/hemapani/ >> Phone: 0772360902 >> > > > > -- > Regards, > > Thushan Ganegedara > School of IT > University of Sydney, Australia > -- Thanks & regards, Nirmal Associate Technical Lead - Data Technologies Team, WSO2 Inc. Mobile: +94715779733 Blog: http://nirmalfdo.blogspot.com/
_______________________________________________ Dev mailing list Dev@wso2.org http://wso2.org/cgi-bin/mailman/listinfo/dev
