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

141–150 of 156 posts

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

#141

Post by dumb1224 »

citilife wrote: post #120
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 am one of those without a PhD, but have taken the time to the learn the math & contribute quite a bit to this area. That being said, I also don't think deep learning itself is not really a "science". The issue I have is you can't predict if a network will learn. We're effectively testing deep learning networks the same way the Romans used to test bridges. Send a bunch of elephants over them, if it holds it's good e…

> We're effectively testing deep learning networks the same way the Romans used to test bridges. Send a bunch of elephants over them, if it holds it's good enough.

Well for human level tasks maybe, but what about other areas of research where we like to discover patterns not seen by a human? Like finding links between genomic interplay with external perturbation such as radiotherapy? It'll be very lucky to have such 'elephants' to test at all.

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

#143

Post by deadliftpro »

osipov wrote: post #65
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?

There were alternatives. IMO, Microsoft Cntk being one which was better than tensorflow. Tensorflow 'won' because of herd mentality and the perception that everything google does is cool.

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

#144

Post by fuzzythinker »

echelon wrote: post #8

I'm doing deep learning without a data science background. Some of my current results are: * https://vo.codes * https://trumped.com The voices need better data curation and longer training, but some speakers such as David Attenborough are quite good. I've also built a real time streaming voice conversion system. I want to generalize it better so that it can be an actual product. I think it could be a killer app for D…

Think HN broke both, getting "server is busy"

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

#145

Post by lostmsu »

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 am using Python's TensorFlow API from C# through my own binding, and I don't understand how you got 250ms latency on C API without screwing up on your side. I could effortlessly run a super real-time network playing a video game with soft actor-critic with my setup on 1.15.

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

#146

Post by sgillen »

robpal wrote: post #42

I attended a conference talk of a FB AI-engineer talking about her paper with backprop equations so obviously wrong my eyes hurt, and incorrect definitions of objects. It did not stop her from participating (btw. this is always unclear -- who did what) in state-of-the art research in object detection. PhD is overrated in the deep learning context. It is more about forging the intellectual resilience and ability to pu…

Don't underestimate useful things, tricks, and theorems though ;)

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

#147

Post by mark_l_watson »

This is very well done, hitting on some pain points and explaining how to work around them.

I have devoted close to 100% of my paid working time on deep learning for the last six years (most recently managing a deep learning team) and not only has the technology advanced rapidly but the online learning resources have kept pace.

A personal issue: after seven years of not updating my Java AI book, I am taking advantage of free time at home to do a major update. New material on deep learning was the most difficult change because there are so many great resources, and there is only so much you can do in one long chapter. I ended up deciding to do just two DL4J examples and then spending most of the chapter just on advice.

The field of deep learning is getting saturated. Recently I did a free mentoring session with someone with a very good educational background (PhD from MIT) and we were talking about needing specializations and specific skills, just using things like DL, cloud dev ops, etc. as necessary tools, but not always enough to base a career on.

Definitely it can help peoples’ careers working through great online DL material, but great careers are usually made by having good expertise in two or three areas. Learn DL but combine that with other skills and domain knowledge.

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

#148

Post by secondcoming »

lostmsu wrote: post #145
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 am using Python's TensorFlow API from C# through my own binding, and I don't understand how you got 250ms latency on C API without screwing up on your side. I could effortlessly run a super real-time network playing a video game with soft actor-critic with my setup on 1.15.

We didn't understand either. One thing, our cloud instances had no GPU's. Our model wasn't exactly complex, just maybe 15 float and string scalar inputs.

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

#149

Post by shrimpx »

listenallyall wrote: post #106
shrimpx wrote: post #96

Earlier quoted context omitted.

It sounds like what you’re complaining about is some people who put papers on arxiv and deceivingly claim to be experts. And kind of implying that these blog posts are to blame, so the blog posts should be retracted due to those dishonest academic people? You’re making a very confusing point.

Not confusing. He's saying that watching Judge Judy for a week doesn't make you a lawyer. And when hiring, be careful because lots of people who claim to be experts are far from it.

That’s valid, but he’s implying that Judge Judy should be taken off air because some people watch it and then pretend to be lawyers. Squelching information seems like a terrible way to eliminate a few impostors downstream.

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

#150

Post by pests »

donquichotte wrote: post #2

Tangentially related (and also using the ubiquitous MNIST dataset), Sebastian Lague started a brilliant, but unfortunately unfinished video series on building neural networks from scratch. This video was an absolute eye-opener me [1] on what classification is, how it works and why a non-linear activation function is required. I probably learned more in the 5 minutes watching this than doing multiple Coursera courses…

One "ah ha" about that required non-linear function I had was the fact that if you were just passing numbers through a series of linear functions they could by definition just be combined into one equation.
Post reply on HN