Unsupervised learning takes samples and generates more of the same kind of data. We can see unsupervised learning as being given samples (X) and training a function X = F(noise) that transforms a random vector into an output whose distribution resembles that of the original generating function.
Reinforcement learning sees a reward R(X) of policies X and learns to find X such that R(X) is high.
All of these have been known to operate on trees or other representations instead of arrays.
This matters because there are business problems that are not supervised learning. Reinforcement learning problems especially. Sometimes I can say how well an output is doing and I want an output that does better.
Yes, exactly.
As a "Pull" programmer [1], I can't tell how I would use this technology to solve problems I have or my company has. This makes it difficult for me to get motivated to learn it, despite all the buzz and excitement.
I went through the tensorflow tutorial. While it is interesting, I didn't find it useful, the way learning a new programming language or framework or library would be.
[1]http://v25media.s3.amazonaws.com/edw519_mod.html#chapter_71
That's one general statement over another. Consider https://arxiv.org/abs/1508.00021 as a counterexample.
...how you implement those functions, how you optimise for the best results and performance is an implementation detail.
If you are picking your solution before you know what your problem is, you are falling into premature optimisation.
Understanding how to reduce your problem domain into a series of functions that take numerical data and return numeric data is the key practical problem that most people face, and it's poorly described in the literature.
(That's why most people just pull out that classic line '...its great for image recognition and ...many other things...')
> because a traditional function implementation of f(x) that takes a I of dimension say, 65535, and produces an output of dimension 1 is a hard problem
Nitpick maybe, but you do not represent each class by a number. This would create a bias to consider subsequent categories as similar (why would aardvark=0 be more similar to antilope=1 than cat=2?). Instead you have one dimension per possible-value (aka one-hot encoding) and the value in that dimension represents how likely the photo belongs to that class (with values summing to 1, softmax, if it's a one-class problem, or no such guarantee if it's a multiclass problem).
> That's. All. It. Does.
No. That's. WHAT. It. Does.
Your emotional overreaction to this site has induced bias leading to a false negative -- mistaking hype for signal. Fact is, using deep learning, newbie grad students have routinely and resoundingly outperformed nearly all the state-of-the-art techniques in signal processing in less than FIVE years of trying. Image analysis and speech recognition have been revolutionized; 40+ years of R&D expertise has been largely supplanted in the blink of an eye. Dismiss this tsunami at your own peril.
Does DL scale to harder problems? Why yes, it does. No computer implementation of the game Go had outperformed the best humans until deep learning was used, then it beat the best humans almost immediately (unlike chess which took decades to reach that level using traditional AI methods). I have little doubt that significant achievements await DL's application to more complex tasks like language analysis too. To believe otherwise would be severely short-sighted.
Does deep learning also solve trivial pattern rec problems like regression or curve fitting as efficiently as some linear ML models? No, but who cares? By that reasoning, we should dismiss Einstein because many 12 year old children can multiply numbers faster and for less money.
I feel https://www.tensorflow.org/tutorials/word2vec is really good example of what I'm actually talking about.
Given a corpus, how do you represent it in a form that is suitable for processing?
Actually, it turns out that's a really hard problem which a lot of work has gone into; but many tutorials and introductions to ML skip over it as though it were a trivial implementation detail on the back of which type of NN you decide to use, or how many layers you want.
I wrote the parent comment because on reading http://aiplaybook.a16z.com/docs/intro/survey-goals, I got excited that maybe someone had actually broached this topic in a meaningful way.
...but then as I read through yet another guide to installing tensorflow followed by assert!(example 101 works), I lost all enthusiasm for it. I don't know; I'm happy to admit I'm perhaps overly critical, but this wasn't a false negative for me, it was just a frustrating unfulfilled promise. Just read the tensorflow tutorials, they're better.
Here's someone else who cherry-picked a quote and ignored the central argument: https://news.ycombinator.com/item?id=14347068
Almost every one of your sentences are talking past the parent. If you want to be argumentative instead of helping the parent as he asked, then it might be best to find actual quotes to disagree with.
The traditional computer vision pipeline works like this: you preprocess the image, featurize it with features like SIFT, and then run an SVM classifier. However, this pipeline is totally beaten by end-to-end neural networks.
Same will hold true for other domains. As long as we've discovered the right architecture, aka. the family for f(x), learning still boils down to training your models.
This and some of your other comments in this thread lead me to believe you are unaware of how DL is being used in NLP. I would argue real industry use of DL for NLP dwarfs that of DL for images. Personal assistants, search, customer service, sales, chat are the big general cases, let alone company-specific tasks (.e.g. financial data, reviews) or other NLP domains that are not particularly industry-adopted (.e.g. translation, summarization). There's a lot of demand for NLP DL experts, and it's no surprise this year that Socher's NLP DL class had 700 Stanford students enrolled.
> Deep learning is a class of machine learning that has gotten a lot of well-deserved attention in recent years because it's working to solve a wide variety of AI problems in vision, natural language processing, and many others.
What others? Be specific.
The problem is not that people don't know how to build neural networks.
The tensorflow tutorial is extremely comprehensive and there are lots of resources for people who know what problem they're solving to try to build a solution.
The problem is that people don't understand what they can do with this technology, or even, in a meaningful sense, what it is.
Given a array of input numbers [i1, i2, i3...] it provides a black box that can map that input to a set of output numbers [o0, o2, ...] where the dimension of the input and output are different.
That's. All. It. Does.
It takes an input array and outputs an output array; a magic f(x) function.
The thing people don't understand well is not how do I implement f(x); the problem is how do I convert my domain problem (I have 2000000 shelf products in my database and a tonnes of sales information) how to convert that into an input array of numbers? What is the output array of numbers I want out of the function?
The reason this works well for images is because you can say, ok, this output number represents a tag (dog, cat, etc) for each discrete value, and the input numbers are just an array of the raw pixel data.
That's why its good for images; because a traditional function implementation of f(x) that takes a I of dimension say, 65535, and produces an output of dimension 1 is a hard problem.
...but if your problem is, given an input of say [price, date, origin] and an output of [value to business], you can solve that problem quite trivially without needing any neural network.
tldr; The problem people are having is figuring out input and output for domains other than image processing; not how to build a NN, or how to choose which NN to build.
Guide misses the point entirely.
(You might argue this is somewhat uncharitable to what is actually a well written guide to ML; but you can read the about section for yourself and see what you think; I feel like the guide needs to focus sharply on practical business outcomes if it wants to do what it says its doing)