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

Facebook AI Research Team Open Source DeepMask and SharpMask

code.facebook.com

Post reply on HN
Print view View original

71–80 of 89 posts

Re: Facebook AI Research Team Open Source DeepMask and SharpMask

#71

Post by RBerenguel »

orthoganol wrote: post #61
said wrote: post #6

Is there any way for those of us with average intelligence to contribute to tools like this? I know I'm a decent developer, but I feel entirely entirely inadequate to participate in this enormous, scary world of AI.

Playing devil's advocate slightly, but as a web developer recently getting into ML over the last year, it's really nothing that fancy. Even the cutting edge like "word2vec using long short term memory neural networks" is still at its heart a "dumb" approach to 'intelligence'... treat the phenomena like a black box, let your system figure out the 'unknown parameters' automatically from data, don't ask too many questio…

I quickly (read everything, didn't solve the exercises, 5 days along several commutes and flights) skimmed Steinwart-Chritmann's Support Vector Machines before joining my current company in case I needed to get into more modern papers, so I could have a decent-ish background in the subject. It's a tough area, and I have an acceptable level in functional analysis.

You are mixing "applying ML black boxes" with "creating ML black boxes". The former is not specially hard (if you know the language the libraries are in, have curiosity and time), but you need to know a little bit of what you are doing unless you want to just be one of the thousand monkeys with a typewriter. The latter is hard, like very hard.

Re: Facebook AI Research Team Open Source DeepMask and SharpMask

#72

Post by cel1ne »

said wrote: post #6

Is there any way for those of us with average intelligence to contribute to tools like this? I know I'm a decent developer, but I feel entirely entirely inadequate to participate in this enormous, scary world of AI.

I found this a very good place to start from scratch: https://cs231n.github.io/

Re: Facebook AI Research Team Open Source DeepMask and SharpMask

#73

Post by sgt101 »

said wrote: post #6

Is there any way for those of us with average intelligence to contribute to tools like this? I know I'm a decent developer, but I feel entirely entirely inadequate to participate in this enormous, scary world of AI.

The wrap, documentation and detail of tools could often be improved, and often the people who have built these tools are focused on their next paper, or their IPO. Some amazing projects have research devs who have extremely high quality thresholds but these amazing teams struggle when faced with the need to deal with the very diverse needs of the wider world - for example three major OS's, five (say) versions of each OS, 5 (say) databases, and so on. If more helpful developers could be focused on helping these projects then that would be fantastic.

The challenge is to find a figure who is not a researcher driving for papers who has authority and experience managing delivery and can engage and orchestrate mainstream contributors. Occasionally these people emerge like a messiah (cf. Linux) but it seems to me that this is one of the hit/miss factors that mean that some of the best "1000 flowers" fail to bloom.

Does Tensorflow have an Open Source project manager employed by Google?

Re: Facebook AI Research Team Open Source DeepMask and SharpMask

#74

Post by orthoganol »

RBerenguel wrote: post #71
orthoganol wrote: post #61

Earlier quoted context omitted.

Playing devil's advocate slightly, but as a web developer recently getting into ML over the last year, it's really nothing that fancy. Even the cutting edge like "word2vec using long short term memory neural networks" is still at its heart a "dumb" approach to 'intelligence'... treat the phenomena like a black box, let your system figure out the 'unknown parameters' automatically from data, don't ask too many questio…

I quickly (read everything, didn't solve the exercises, 5 days along several commutes and flights) skimmed Steinwart-Chritmann's Support Vector Machines before joining my current company in case I needed to get into more modern papers, so I could have a decent-ish background in the subject. It's a tough area, and I have an acceptable level in functional analysis. You are mixing "applying ML black boxes" with "creatin…

I'm not sure what you mean by "creating ML black boxes", since I don't think most people working in ML are required to invent new types of ML approaches, in the same way that Rails, Django, Sails works for most web apps. It's pretty straightforward to learn the ancillary data preparation, cross-validation, etc, and at the very least you can quickly apply a wide array of ML techniques (KNN, decision trees, LR, neural nets, etc.) with 3,4 LOC each (frameworks) and compare results, an approach you sometimes see on Kaggle. There's a reason "data science" bootcamps are putting out thousands of attendees on the job market - it's straightforward enough to get someone in the door for an interview after a few months of hard work (assuming they have either a strong programming or strong stats background).

Re: Facebook AI Research Team Open Source DeepMask and SharpMask

#75

Post by RBerenguel »

orthoganol wrote: post #74
RBerenguel wrote: post #71

Earlier quoted context omitted.

I quickly (read everything, didn't solve the exercises, 5 days along several commutes and flights) skimmed Steinwart-Chritmann's Support Vector Machines before joining my current company in case I needed to get into more modern papers, so I could have a decent-ish background in the subject. It's a tough area, and I have an acceptable level in functional analysis. You are mixing "applying ML black boxes" with "creatin…

I'm not sure what you mean by "creating ML black boxes", since I don't think most people working in ML are required to invent new types of ML approaches, in the same way that Rails, Django, Sails works for most web apps. It's pretty straightforward to learn the ancillary data preparation, cross-validation, etc, and at the very least you can quickly apply a wide array of ML techniques (KNN, decision trees, LR, neural…

Brief, on phone: my view of the comment addressed is that it is different doing stuff with ML that on ML, and I thought on was the addressed topic, not with

Re: Facebook AI Research Team Open Source DeepMask and SharpMask

#76

Post by genofon »

orthoganol wrote: post #61
said wrote: post #6

Is there any way for those of us with average intelligence to contribute to tools like this? I know I'm a decent developer, but I feel entirely entirely inadequate to participate in this enormous, scary world of AI.

Playing devil's advocate slightly, but as a web developer recently getting into ML over the last year, it's really nothing that fancy. Even the cutting edge like "word2vec using long short term memory neural networks" is still at its heart a "dumb" approach to 'intelligence'... treat the phenomena like a black box, let your system figure out the 'unknown parameters' automatically from data, don't ask too many questio…

well that's not "contributing to the field", is just being a developer using libraries. The OP is talking about creating something new, which is like contributing to physics: quite hard, and requires a lot of knowledge. Maybe you don't need to be a genius (although the field attract quite a bit of them, tough competition) but surely a lot of effort.

Re: Facebook AI Research Team Open Source DeepMask and SharpMask

#77

Post by pmontra »

said wrote: post #6

Is there any way for those of us with average intelligence to contribute to tools like this? I know I'm a decent developer, but I feel entirely entirely inadequate to participate in this enormous, scary world of AI.

Many people already answered you. I add that there is another barrier to entry: the hardware you have could not be able to run the software.

A requirement for this one is an NVIDIA GPU with compute capability 3.5+. It turns out that my NVIDIA GPU is a 3.0 one (a laptop with a Quadro K1100M). I'm half lucky, because my laptop lets me upgrade the GPU (it's a HP zBook), still do I want to spend the money only to experiment? I didn't check the price for a 3.5+ GPU that fits in my laptop but you can compare this to cloning a pure-CPU repository from GitHub and give it a try.

As GPUs are used more and more for computing tasks, it feels more and more like back in the 80s when you found a nice 6502 assembly program on a magazine but your CPU was a Z80 (or 68000 and you had 80286). We eventually standardized on x86/amd64 because the market went there. I wonder if we're going to standardize on a GPU architecture too.

By the way, before somebody points it out, a solution is to get a cloud GPU server (AWS has them). Still I'd like to be able to develop locally.

Re: Facebook AI Research Team Open Source DeepMask and SharpMask

#78

Post by pmontra »

swframe wrote: post #70

Is there a link to get the code?

Click the links in the "We're making the code for DeepMask+SharpMask as well as MultiPathNet" line. They should have made them display more prominently.

They require to login to FB, then redirect to GitHub

https://github.com/facebookresearch/deepmask

https://github.com/facebookresearch/multipathnet

Re: Facebook AI Research Team Open Source DeepMask and SharpMask

#79

Post by disgruntledphd2 »

visarga wrote: post #52
kmike84 wrote: post #35

Earlier quoted context omitted.

ML can be an useful skill for developer. Think of it as of linux / sysadmin skills, or as web design / UI skills - they are all quite different from software development, but many software devs have them. I think that applied ML slowly becomes a similar thing - an useful tool in a toolbelt. It takes time to become really good at it, but basics are relatively easy to aquire. Libraries and learning resources are much b…

> but you don't have to know all state of the arts techniques to be dangerous Often times you can be dangerous with just scikit learn, xgboost and Keras if you can do data prepping, pipelines and stacking/ensembles. Besides wonderful frameworks such as TF, Theano and Torch there are also "zoos" of ready made models, word vectors and such that can be used out of the box.

Do read introduction to statistical learning though, as that book helps to give (some) understanding of what's actually happening in the models, which is important when (not if) things go horribly wrong.

Re: Facebook AI Research Team Open Source DeepMask and SharpMask

#80

Post by haraball »

magicalist wrote: post #11
said wrote: post #6

Is there any way for those of us with average intelligence to contribute to tools like this? I know I'm a decent developer, but I feel entirely entirely inadequate to participate in this enormous, scary world of AI.

> Is there any way for those of us with average intelligence to contribute to tools like this? The people doing this aren't magical geniuses; they've just put the time and work into the subject and have been able to get themselves into a position they can do this all day surrounded by others they can collaborate with. As with most human endeavors, the trick is to just get started, and not get frustrated and give up w…

The course on coursera uses Octave for the exercises. This guy has rewritten all the exercises in Python: http://www.johnwittenauer.net/machine-learning-exercises-in-...
Post reply on HN