The Difference Between AI, Machine Learning, and Deep Learning
blogs.nvidia.com
The Difference Between AI, Machine Learning, and Deep Learning
1–10 of 107 posts
Re: The Difference Between AI, Machine Learning, and Deep Learning
#2Why the hell is the text not black? It's very awful to read on mobile..
Re: The Difference Between AI, Machine Learning, and Deep Learning
#3Has anyone figured out how to debug and/or analyze deep ANN?
That's the problem I always had, you may get them into a trained state, but good luck figuring out any reason 'why' they ended up in that state (or even what that state really is).
Re: The Difference Between AI, Machine Learning, and Deep Learning
#4Deep learning is just a rebranding of "neural networks". When neural nets became unpopular in the 90s and early 2000s, people talked about "multilayer networks" (dropping the "neural") since it wasn't really useful to think about this approach from the neuro perspective (since it's such a cartoonish model of real neural networks anyway).
Now that very deep networks have become possible, and various graphical models and Bayesian approaches have also been folded under "deep learning" (for example, using back-propagation to learn complicated posterior distributions in variational Bayes) deep learning is not just about vanilla feedforward nets.
Re: The Difference Between AI, Machine Learning, and Deep Learning
#5Has anyone figured out how to debug and/or analyze deep ANN? That's the problem I always had, you may get them into a trained state, but good luck figuring out any reason 'why' they ended up in that state (or even what that state really is).
IMO that's not really the point of deep learning. I'm not saying no efforts have been made to work towards better understanding, but the types of problems deep learning is good at I do not believe have easily explainable answers.
There are machine learning methods out there that are much better at explaining why, but fail hard on problems that DNN is good at.
IMHO, this is the nature of the problem, not the solution.
Re: The Difference Between AI, Machine Learning, and Deep Learning
#6I disagree. Machine learning is more general than AI and therefore should be the outer circle (unless you believe the meme "did a regression - called it AI")
Deep learning is, yes, a subcase of machine learning, and AI may be a circle within machine learning and enclose deep learning.
But truth be told, we will all regret the way we use the term AI now. Eventually the term AI will refer only to general intelligence (aka AGI).
Re: The Difference Between AI, Machine Learning, and Deep Learning
#7I disagree. Machine learning is more general than AI and therefore should be the outer circle (unless you believe the meme "did a regression - called it AI") Deep learning is, yes, a subcase of machine learning, and AI may be a circle within machine learning and enclose deep learning. But truth be told, we will all regret the way we use the term AI now. Eventually the term AI will refer only to general intelligence (…
Machine learning and AI are two overlapped fields, it's hard to say one completely encompasses the other. So two overlapped circle would be better?
Re: The Difference Between AI, Machine Learning, and Deep Learning
#8I disagree. Machine learning is more general than AI and therefore should be the outer circle (unless you believe the meme "did a regression - called it AI") Deep learning is, yes, a subcase of machine learning, and AI may be a circle within machine learning and enclose deep learning. But truth be told, we will all regret the way we use the term AI now. Eventually the term AI will refer only to general intelligence (…
I think the author's illustration is technically correct, given the currently widely adopted definition of AI and its subfields.
However, you do have a point that simple machine learning aka linear regression is not really "Artificial Intelligence" if you raise the expectation of "Artificial Intelligence".
Re: The Difference Between AI, Machine Learning, and Deep Learning
#9Has anyone figured out how to debug and/or analyze deep ANN? That's the problem I always had, you may get them into a trained state, but good luck figuring out any reason 'why' they ended up in that state (or even what that state really is).
> That's the problem I always had, you may get them into a trained state, but good luck figuring out any reason 'why' they ended up in that state (or even what that state really is).
Can you give a specific example of what you mean? I ask because I see this sentiment often, but primarily from people who are very new to deep learning.
You can definitely debug a neural network. You mostly want to look at metrics from training such as gradient norms or try adjusting parameters to see if you can get a gain in overall performance as measured by cross validation performance.
You can definitely analyze a neural network. You do so by forming hypotheses, preparing datasets that reflect those hypotheses, and running them through your trained models, noting cross validation performance. It's also possible to visualize the weights in various ways, there are many papers written about it.
So what do you mean exactly when you say no one has figured out how to debug or analyze DNNs?
Re: The Difference Between AI, Machine Learning, and Deep Learning
#10I disagree. Machine learning is more general than AI and therefore should be the outer circle (unless you believe the meme "did a regression - called it AI") Deep learning is, yes, a subcase of machine learning, and AI may be a circle within machine learning and enclose deep learning. But truth be told, we will all regret the way we use the term AI now. Eventually the term AI will refer only to general intelligence (…
Eventually.. eventually, we will drop the A too.