Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Activity
  • Oct 02 18:47
    sarony removed as member
  • Oct 02 17:45
    erictleung commented #82
  • Aug 15 11:17
    FrednandFuria opened #82
  • Jun 20 21:19
    @bjorno43 banned @shenerd140
  • May 10 09:13
    @bjorno43 banned @zhaokunhaoa
  • Apr 27 19:48
    @mstellaluna banned @zhonghuacx
  • Apr 25 17:07
    @mstellaluna banned @cmal
  • Jan 08 22:07
    @mstellaluna banned @gautam1858
  • Jan 08 22:05
    @mstellaluna banned @dertiuss323
  • Dec 15 2018 23:34
    @mstellaluna banned @Julianna7x_gitlab
  • Oct 12 2018 05:50
    @bjorno43 banned @NACH74
  • Oct 05 2018 23:02
    @mstellaluna banned @JomoPipi
  • Sep 16 2018 12:21
    @bjorno43 banned @yash-kedia
  • Sep 16 2018 12:16
    @bjorno43 banned @vnikifirov
  • Sep 05 2018 08:13
    User @bjorno43 unbanned @androuino
  • Sep 05 2018 07:38
    @bjorno43 banned @androuino
  • Aug 23 2018 16:58
    User @bjorno43 unbanned @rahuldkjain
  • Aug 23 2018 16:23
    @bjorno43 banned @rahuldkjain
  • Jul 29 2018 14:15
    User @bjorno43 unbanned @jkyereh
  • Jul 29 2018 01:00
    @bjorno43 banned @jkyereh
phao5814
@phao5814
hey guys - would appreciate it if someone with experience in CNNs could help clarify this for me :) https://stackoverflow.com/questions/57038055/what-are-activations-activation-gradients-weights-and-weight-gradients
Juliana Marie
@julianamariemorales
Hi guys, what is your suggested minimum data to be in a cluster?
Philip Durbin
@pdurbin
I went to a "Intro to Data Science: Predict the Box Office" workshop last night and the slides and Jupter Notebook they used are linked from https://www.thinkful.com/workshops/city/box-office/ . Pretty interesting stuff. Pandas, scikit-learn, etc.
Alice Jiang
@becausealice2
@julianamariemorales I feel like that would be subjective, I don't think anyone can give you a solid answer...
@pdurbin Oooohhhhh.... I've had my eye on their meetups for quite some time but haven't actually gone yet. Would you recommend?
Philip Durbin
@pdurbin
The speaker had a somewhat heavy accent but seemed to really know what he was talking about. Sure, I'd recommend it.
Alice Jiang
@becausealice2
fabulous
Philip Durbin
@pdurbin
It was on the 6th floor. Decent view.
Alice Jiang
@becausealice2
I imagine so. I love back bay. Anytime I go exploring I almost always end up wandering around there
Philip Durbin
@pdurbin
Yeah, my wife and I lived in the Fenway for four years and we'd wander over there a lot.
Alice Jiang
@becausealice2
I'm looking through that notebook now and.... what movie was eight and a half hours?!
Alice Jiang
@becausealice2
This one is listed in the dataset as being more than eight and a half hours long lol
oh wait it's a TV series.. Why is it in a boxoffice dataset?
Philip Durbin
@pdurbin
dunno
Seems like a fun dataset though. I like movies. :)
Alice Jiang
@becausealice2
It needs to be looked at and cleaned a bit lol I've really only looked at durations and I've found a few that are very wrong
Philip Durbin
@pdurbin
He had many, many slides on data cleansing.
Alice Jiang
@becausealice2
I haven't looked through the slides yet
but there's a bunch of TV series and the wolf of wallstreet is listed at 4 hours long lol
it's just a list of 5k random titles I think, there's tons of titles an hour and under and I recognize most of them as TV series
Alice Jiang
@becausealice2
it appears that the data cleaning process eliminates most, if not all non-movies so don't mind me complaining :joy:
Philip Durbin
@pdurbin
heh
@julianamariemorales hi there! What do you mean by "cluster"? Like a computer cluster or an unsupervised learning cluster?
Eric Leung
@erictleung
@phao5814 I took a try at explaining an answer to your question https://stackoverflow.com/a/57085350/6873133
vsvd
@vsvd
Hi, Are there any tools(Open source) for generating test data for page view for ML algorithm. For now I am trying to write a selenium test to view different products randomly in a website. So that way, i can generate VIEW ACTION logs for the Machine Learning Algorithm. I am expecting by doing this way, it will take lot lot of time to generate bulk data/log (More than one million logs in DB). Is there any Data Generation tool/open source tool for above scenario.
Alice Jiang
@becausealice2
I just read a Kotaku article on gaming sustainability that included some information on data center efficiency. You guys ever considered how eco-friendly your cloud computing is(n't) before?
@vsvd you're looking for an open source tool to generate bogey data based on existing data?
Vishesh Mangla
@XtremeGood
anyone here?
phao5814
@phao5814
hey everyone, would appreciate if anyone with experience at writing custom loss functions in keras can help me out here! https://stackoverflow.com/questions/57248667/valueerror-an-operation-has-none-for-gradient-while-implementing-custom-loss
Mazzy7
@Mazzy7
Hello!! I want to use a regression model with flutter but I am getting an error when I am running the
Tflite.runModelOnImage
Shall I provide label.txt file
Alice Jiang
@becausealice2
@Mazzy7 Flutter for building native apps?
IssaMousssa
@IssaMousssa
I want to do linear regression but I have a nominal variable. Do I have to use OneHotEncoder or is StringIndexer sufficient? I use pyspark
Alice Jiang
@becausealice2
I don't know anything about stringindexer off the top of my head, I think one hot encoding could work @IssaMousssa
quick glance at google search results make it seem like StringIndexer could also be a solution
Vishesh Mangla
@XtremeGood
hi someone here?
and knowing tensorflow 2.0?
Alice Jiang
@becausealice2
here, yes. TF2.0, not so much I'm afraid :(
Vishesh Mangla
@XtremeGood
hi can I get some help about posting on stackoverflow
?
Again and again I ' m getting error on formatting.
Alice Jiang
@becausealice2
what error?
Janus Reith
@janus-reith

Hi, I'm pretty new to ML and trying to find out if my use case is already implemented and available to use.
Specifically I'd search something js based to use with node, like brain.js or tensorflow-js.

Im looking for a specific usecase to implement: I have a text and want to extract multiple specifications from that.
Probably it will use LSTM, but I would need multiple outputs for my input

It would be awesome if it could work in such a way:
Input: "Intel Core i7-7500U 2,70 GHz, 16 GB DDR4"
Output: { cpuManufactor: "Intel", cpuClockRate: "2,70", "memorySize": 16, "memoryType": "DDR4" }

The input wouln't always have the same length or contain the same information.

If it wouldn't work this way I could settle for a less dynamic pattern like:
Output: { cpuManufactorIntel: 1, cpuClockRateIs270: 1, memorySizeIs16: 1 memoryTypeIsDDR4: 1 }

However, getting near the first example would be awesome.

As the concept behind this text classification is pretty general and not related to my specific data I believe something similar to this must be implemented somewhere already.
However I didn't really find anything yet.

Thanks in advance for your help!

Alice Jiang
@becausealice2
I've never seen anything like that specific example, @janus-reith but it sounds like you're looking for some type of feature extraction?
Janus Reith
@janus-reith
@becausealice2 Yeah, I had to to look it up, but this seems to be what I am looking for
Janus Reith
@janus-reith

IMHO this should work without a dictionary and without actual language processing.

Just that I have enough training data similar to "Intel Core i7-7500U 2,70 GHz, 16 GB DDR4" resulting in { cpuClockRate: "2,70", "memorySize": 16 }
or similar examples like "Intel Core i7-2500U 1,80 GHz, 8 GB DDR4" resulting in { cpuClockRate: "1,80", "memorySize": 8 } so new Entries could be matched with a certain similarity