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

TensorFlow, Keras and deep learning, without a PhD

codelabs.developers.google.com

Post reply on HN
Print view View original

61–70 of 156 posts

Re: TensorFlow, Keras and deep learning, without a PhD

#61

Post by mpfundstein »

gas9S9zw3P9c wrote: post #31

As a researcher in the field I am not quite sure how I feel about these kind of resources. I am all for making research accessible to a wider audience and I believe that you don't need a PhD, or any degree, to do meaningful work. At the same time, the low barrier of entry and hype has resulted in a huge amount of people downloading Keras, copying a bunch of code, tuning a few parameters, and then putting their result…

by far thr worst part of Deep Learning research is the flood of crappy papers. i dont want to know how much time i wasted on reading through papers with math errors or trying to replicate results without success. and even if github code is available, i assure you. 95% of the time the code doesnt even work without major fixes.

oh i hate it :-)

so i started filtering. one pretty good filter is: only chinese authors from chinese universities? -> nope!

Re: TensorFlow, Keras and deep learning, without a PhD

#62

Post by melenaboija »

gas9S9zw3P9c wrote: post #31

As a researcher in the field I am not quite sure how I feel about these kind of resources. I am all for making research accessible to a wider audience and I believe that you don't need a PhD, or any degree, to do meaningful work. At the same time, the low barrier of entry and hype has resulted in a huge amount of people downloading Keras, copying a bunch of code, tuning a few parameters, and then putting their result…

I agree in some sense but I also think that everybody has the right to learn at any level, mainly because not everything in neural networks field is research to create the next optimizer or a new architecture.

This is perfect for the people I work with and the role we have (and I am talking about some of them are PhDs in math and physics but without much CS knowledge). Some of this people just need to see this is a stack of non linear functions that have to be minimized and they grasp the idea of nn really fast.

To me this would be like saying that if you don't know computational complexity theory or how compilers work you are not a good software developer, but I think is just a different level and as long as you don't try to inflate your resume is fine.

Sometimes I feel some fear on AI field when the knowledge is spread, and there is a bunch of backgrounds (maths, physics, quantitative finance, chemistry, ...) that need exactly this to at list demistify nn.

Re: TensorFlow, Keras and deep learning, without a PhD

#63

Post by pachico »

gas9S9zw3P9c wrote: post #31

As a researcher in the field I am not quite sure how I feel about these kind of resources. I am all for making research accessible to a wider audience and I believe that you don't need a PhD, or any degree, to do meaningful work. At the same time, the low barrier of entry and hype has resulted in a huge amount of people downloading Keras, copying a bunch of code, tuning a few parameters, and then putting their result…

I guess the same could be argued for coding, in general. I myself don't have a degree in CS yet I can tell amateur code from well designed one (unless I have fooled everyone in the last 20 years!). The industry has ways to filter sloppy work, somehow, I wouldn't worry too much about it. I would, instead, include the necessity of being able to judge good from bad in this fieald too, as it's always been for everything else.

Re: TensorFlow, Keras and deep learning, without a PhD

#64

Post by amelius »

gas9S9zw3P9c wrote: post #31

As a researcher in the field I am not quite sure how I feel about these kind of resources. I am all for making research accessible to a wider audience and I believe that you don't need a PhD, or any degree, to do meaningful work. At the same time, the low barrier of entry and hype has resulted in a huge amount of people downloading Keras, copying a bunch of code, tuning a few parameters, and then putting their result…

Well, maybe I got the wrong impression but after reading the (very accessible) Yolo V3 paper [1], it seems to me that even the experts do little real math and lots of guesswork, kicking a model until it starts giving results.

[1] https://pjreddie.com/media/files/papers/YOLOv3.pdf

Re: TensorFlow, Keras and deep learning, without a PhD

#65

Post by osipov »

secondcoming wrote: post #43

It's a pity that most Tensorflow tutorials out there seem to deal with images. We tried to use it for real-time data classification (data -> [yes | no]). Every tuturial out there seems to assume you're using Python (which is probably not an invalid assumption). Here's my 2c when trying to use Tensorflow with C++: a) Loading SavedModels is a pain. I has to trawl the Tensorflow repo and Python wrappers to see how it wo…

I don't understand why you are getting downvoted. TensorFlow 1.x barely worked and people stuck with it because the alternatives were worse. I moved to PyTorch as soon as I could because it is better than TensorFlow 1.x, TensorFlow 2.x, or Keras w/TensorFlow backend.

TensorFlow is designed by committee and is more of a brand now than a machine learning framework. Did you know there is TensorFlow Quantum?

Re: TensorFlow, Keras and deep learning, without a PhD

#66

Post by mpfundstein »

xvzwx wrote: post #15
wirrbel wrote: post #7

The whole AI/ML stuff has become so hyped up that its probably time to find another topic of interest in software engineering for me. Its a weird melange nowadays where frameworks and "academic credentials" are fused together by major tech companies and leaves me - who has deployed a dozen of classical ML models into production that are still running after couple of years - wondering what this is all about. Overall,…

Its true that with todays Frameworks and easy API calls almost everyone with a little technological background can deploy a ML/AI model and get sufficiant results. But Bootcamps cannot replace an academic education. As soon as you are not able to understand and review new released papers and insights and have to wait for an high level blog entry or video course on that topic you are worth nothing. Without a deeper un…

you don't get sufficient results. at least not sufficient to base business decisions on.

this is precisely the myth discussed in this post.

Re: TensorFlow, Keras and deep learning, without a PhD

#67

Post by osipov »

m0zg wrote: post #26

Mandatory plug: do consider using PyTorch instead. It's far easier to pick up and work with. Easy things are easy, hard things are possible.

Agreed. I used TensorFlow 1.x before PyTorch matured. Today, all of my deep learning is PyTorch based because TensorFlow 2.x didn't fix the core TensorFlow 1.x issues (e.g., poor reproducibility, unintuitive API design) and PyTorch performs better than Keras w/TensorFlow backend.

Re: TensorFlow, Keras and deep learning, without a PhD

#68

Post by gas9S9zw3P9c »

amelius wrote: post #64
gas9S9zw3P9c wrote: post #31

As a researcher in the field I am not quite sure how I feel about these kind of resources. I am all for making research accessible to a wider audience and I believe that you don't need a PhD, or any degree, to do meaningful work. At the same time, the low barrier of entry and hype has resulted in a huge amount of people downloading Keras, copying a bunch of code, tuning a few parameters, and then putting their result…

Well, maybe I got the wrong impression but after reading the (very accessible) Yolo V3 paper [1], it seems to me that even the experts do little real math and lots of guesswork, kicking a model until it starts giving results. [1] https://pjreddie.com/media/files/papers/YOLOv3.pdf

Oh yes, I don't think advanced math is required in any way. However, there is a difference in that researchers who have worked with these models for many years (often including having done some of the math) have a very good intuitive understanding of these models. Once you have that, it's fine to be driven by gut feeling. Just like many engineers are driven by gut feeling that come from tacit knowledge through experience.

What is dangerous is reading a 30 minute blog post and getting the illusion of having some kind of understanding, when in reality it can take years to develop that. It's like cloning the postgres Github repository, compiling it, running a few queries, and then saying you've built databases and being hired to become the "database expert" at some company, spreading wrong knowledge left and right.

That's why the popularization of these quick immediate reward tutorials is dangerous. It takes time and effort to become knowledgable at something. Of course, many people are smart enough to know that these tutorials (or cloning the postgres repo) is just the first step on a longer learning journey, and in that case it's totally fine, but there are also many people who start thinking they are experts ready to work on research or production models after going through such things, not being aware of the many things they don't know [0]

[0] https://upload.wikimedia.org/wikipedia/commons/thumb/4/46/Du...

Re: TensorFlow, Keras and deep learning, without a PhD

#70

Post by matlo »

This is a nice introduction, even though as most of the tutorials on ML it goes from 0 to 100 in 2 lessons.

A couple years ago I started studying ML, and I have a design background, so I needed to digest all the math and concepts slowly in order to understand them properly.

Now I think I understand most of the fundamental concepts, and I've been using it quite a lot for creative applications and teaching, and I have to say the best resource I've found for beginners, by far, is "Make Your Own Neural Network" by Tariq Rashid.

It starts really from the beginning and it takes you through all the steps of building a NN from zero, with no previous knowledge. really good.

Post reply on HN