Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Microsoft Cognitive Toolkit 2.0

microsoft.com

Post reply on HN
Print view View original

11–20 of 53 posts

Re: Microsoft Cognitive Toolkit 2.0

#11

Post by KirinDave »

thr0waway1239 wrote: post #8
ronjouch wrote: post #2

Also, "Reasons to Switch from TensorFlow to CNTK": https://docs.microsoft.com/en-us/cognitive-toolkit/reasons-t...

"Many other toolkits create examples that appears to be identical to the original implementation of a paper, and then offer a converted model for people to download and evaluate. This is highly irresponsible in our opinion. In CNTK we pay a lot of attention in tracking down bugs and make sure the toolkit can be used to actually train the model from scratch and achieve state-of-the-art accuracy. One example is the Inc…

Uhh...

Classic hacker news right here.

I'm fairly sure you don't realize what a major problem reproducible results is for the scientific and ML community, but it's big. A commitment to this and transparency is a pretty big deal.

Re: Microsoft Cognitive Toolkit 2.0

#12

Post by eob »

thr0waway1239 wrote: post #8
ronjouch wrote: post #2

Also, "Reasons to Switch from TensorFlow to CNTK": https://docs.microsoft.com/en-us/cognitive-toolkit/reasons-t...

"Many other toolkits create examples that appears to be identical to the original implementation of a paper, and then offer a converted model for people to download and evaluate. This is highly irresponsible in our opinion. In CNTK we pay a lot of attention in tracking down bugs and make sure the toolkit can be used to actually train the model from scratch and achieve state-of-the-art accuracy. One example is the Inc…

As a former ML researcher, I read your quoted text and came away with the exact opposite conclusion. There is an incredible need as a community to work toward reproducible results.

Pull a researcher aside, and I bet you every one will have at least one experience of trying to reproduce some reported--sometimes even lauded--result but being unable to.

The good news is this kind of cultural fix is really invariant of compute platform or modeling framework. It's just nice that MSFT appears to be making it a priority.

Re: Microsoft Cognitive Toolkit 2.0

#14

Post by cbasoglu »

verdverm wrote: post #7

Love the pure (realistic?) linear scaling of "projected" performance​ in the graph

The only reason for projection here was the newness of the Volta HW (announced 2 weeks ago). The linear scaling is proven on Pascal and Maxwell HW and due to the communication library and algorithms like Block Momentum. Note: I am a MSFT employee.

Re: Microsoft Cognitive Toolkit 2.0

#16

Post by it_learnses »

mtw wrote: post #15
it_learnses wrote: post #13

I am a .net developer, and would like to learn it, but not sure how. Any suggestions to where can I access a dataset and the computing power?

I suggest following a machine learning / deep learning course first then learn this

I actually did take a data mining course a couple years ago in uni, and also at the time I was following Andrew Ng's course. TBH, I learn better by working on a project. Otherwise I lose interest midway.

Re: Microsoft Cognitive Toolkit 2.0

#17

Post by sayanpa »

it_learnses wrote: post #16
mtw wrote: post #15

Earlier quoted context omitted.

I suggest following a machine learning / deep learning course first then learn this

I actually did take a data mining course a couple years ago in uni, and also at the time I was following Andrew Ng's course. TBH, I learn better by working on a project. Otherwise I lose interest midway.

If a course is of interest, we will be launching a deep learning course shortly that would help bridge the gaps. Stay tuned. I am a Microsoft employee.

Re: Microsoft Cognitive Toolkit 2.0

#18

Post by mtgx »

I wonder if Tensorflow 2.0 is about to drop soon, too, with Caffe and Cognitive Toolkit now reaching version 2. I also assume it's going to be a lot more than a version change, too.

Re: Microsoft Cognitive Toolkit 2.0

#20

Post by cscurmudgeon »

eob wrote: post #12
thr0waway1239 wrote: post #8

Earlier quoted context omitted.

"Many other toolkits create examples that appears to be identical to the original implementation of a paper, and then offer a converted model for people to download and evaluate. This is highly irresponsible in our opinion. In CNTK we pay a lot of attention in tracking down bugs and make sure the toolkit can be used to actually train the model from scratch and achieve state-of-the-art accuracy. One example is the Inc…

As a former ML researcher, I read your quoted text and came away with the exact opposite conclusion. There is an incredible need as a community to work toward reproducible results. Pull a researcher aside, and I bet you every one will have at least one experience of trying to reproduce some reported--sometimes even lauded--result but being unable to. The good news is this kind of cultural fix is really invariant of c…

I have to agree with your comment fully. Read the comment above and went WTF.
Post reply on HN