41–50 of 94 posts
I'll chip in with my book, which is written with programmers in mind, implements everything from scratch, works on CPU and GPU, at great speed. Directly links theory to implementation, and you can use it along with Goodfellow's Deep Learning book. Also, discusses all steps, and does not skip gradients by using autograd. Deep Learning for Programmers: An Interactive Tutorial with CUDA, OpenCL, DNNL, Java, and Clojure.…
I'll chip in with my book, which is written with programmers in mind, implements everything from scratch, works on CPU and GPU, at great speed. Directly links theory to implementation, and you can use it along with Goodfellow's Deep Learning book. Also, discusses all steps, and does not skip gradients by using autograd. Deep Learning for Programmers: An Interactive Tutorial with CUDA, OpenCL, DNNL, Java, and Clojure.…
Is there a print version (in the planning)? I usually don’t buy ebooks
As an engineer I find myself in this type of situation quite often - if anyone can point me to some good resources or has any advice, I'd be quite grateful: - Some non-technical stakeholder comes to me and says "can we solve this problem with Machine Learning?" usually it's something like "there need to be two supervisors on the factory floor at all times, and I want an email alert everytime there are less than 2 sup…
There are a load of questions here. > Where do I go from here? Keep trying different models? > ...after [the labeling is] all done is this even going to work? > [How to label] > If we spend all this time and money labelling footage, how well is this going to work? How much footage do we need to label? Generally, you're discussing the space of model improvement and refinement. This is the costliest and most dangerous…
It has been challenging communicating many of these realities to non-technical folks, who seem to be quite misguided about implementing these types of systems as opposed to "non-ML" systems where there is a less imperfect and more predictable idea of what's possible, how well it will work, and how much effort is required to pull it off.
Earlier quoted context omitted.
There are a load of questions here. > Where do I go from here? Keep trying different models? > ...after [the labeling is] all done is this even going to work? > [How to label] > If we spend all this time and money labelling footage, how well is this going to work? How much footage do we need to label? Generally, you're discussing the space of model improvement and refinement. This is the costliest and most dangerous…
Gee, you just described my practice :-)
As an engineer I find myself in this type of situation quite often - if anyone can point me to some good resources or has any advice, I'd be quite grateful: - Some non-technical stakeholder comes to me and says "can we solve this problem with Machine Learning?" usually it's something like "there need to be two supervisors on the factory floor at all times, and I want an email alert everytime there are less than 2 sup…
Start by labeling some data yourself. If you need to scale things up, you're going to need very clear rubrics for how things should be labeled and you're not going to be able to make them without having labeled some data yourself.
Definitely think about what the easiest form of your task is. Labeling bounding boxes is time intensive, labeling whether there are 2 or more supervisors on the floor should be a lot easier, and you can easily label a bunch of frames all at once.
You're going to need to figure out what tooling you will need for labeling, is this available out of the box, or will you need something custom?
Label X data points yourself and do some transfer learning. Label another X data points and see how much better things get.
The rough rule of thumb is performance increases logarithmically with data[1]. After you have a few points on the curve about how much better things get from more data, fit a logarithmic curve and make a prediction of how much data you will need, though be prepared that you might be off by a factor of 10.
As others have mentioned, it's worth thinking about false positive/negative tradeoffs and how much you care about either.
If the numbers you're extrapolating to aren't satisfactory, then yeah, you need to keep messing around with your training until you bend the curve enough that it seems like you'll get there with labeled data.
[1] https://ai.googleblog.com/2017/07/revisiting-unreasonable-ef...
As an engineer I find myself in this type of situation quite often - if anyone can point me to some good resources or has any advice, I'd be quite grateful: - Some non-technical stakeholder comes to me and says "can we solve this problem with Machine Learning?" usually it's something like "there need to be two supervisors on the factory floor at all times, and I want an email alert everytime there are less than 2 sup…
I'm somewhat surprised at the responses for this. I believe your issue can be easily solved - have supervisors wear a distinctive color from a non-supervisor. For example let's say it's yellow. OK so now you have yellow wearing supervisors and everyone else. To resolve the issue you have described acquire a month or so of footage, with labels per minute describing how many yellow wearing supervisors and how many peop…
Earlier quoted context omitted.
There are a load of questions here. > Where do I go from here? Keep trying different models? > ...after [the labeling is] all done is this even going to work? > [How to label] > If we spend all this time and money labelling footage, how well is this going to work? How much footage do we need to label? Generally, you're discussing the space of model improvement and refinement. This is the costliest and most dangerous…
Thanks - this validates many of the assumptions I had about this part of the process. It has been challenging communicating many of these realities to non-technical folks, who seem to be quite misguided about implementing these types of systems as opposed to "non-ML" systems where there is a less imperfect and more predictable idea of what's possible, how well it will work, and how much effort is required to pull it…
Earlier quoted context omitted.
Is there a print version (in the planning)? I usually don’t buy ebooks
Only a limited hand-crafted hardcover edition is planned. That being said, you can print a dead tree version from the PDF at your local printing shop (or at home) if you care about the text, and not that much about binding.
Earlier quoted context omitted.
I'm somewhat surprised at the responses for this. I believe your issue can be easily solved - have supervisors wear a distinctive color from a non-supervisor. For example let's say it's yellow. OK so now you have yellow wearing supervisors and everyone else. To resolve the issue you have described acquire a month or so of footage, with labels per minute describing how many yellow wearing supervisors and how many peop…
"Easily solved - just have them wear special clothes." Everything is easy if you can arbitrarily change the requirements!
Remember, the problem is "I need to know when I don't have two managers on the floor," not "how do I use machine learning to know when I don't have two managers on the floor."
Earlier quoted context omitted.
The shocking thing that at least I ran into is the sheer quantity of training data you really need. The large companies doing this successfully are using utterly gigantic libraries of training data that are beyond anything others could ever come up with. It really brought home to me what a blunt intstrument deep learning really is.
Is there some kind of rule of thumb for a minimum of how much data is needed for various types of problems?