Related
I have a good basis on Evolutionary Algorithms, so now i started to read about Artificial Neural Networks. I come across this tutorial on
http://www.ai-junkie.com/ann/evolved/nnt2.html,
showing how to use a ANN to evolve Tanks that collect mines. It uses a GA to evolve the input weights on each Neuron.
I know i could use GA (without the ANN) to solve the same problem. I already created a Tetris Bot using only GA to optimize the weights in the grid evaluation function (check my blog http://www.bitsrandomicos.blogspot.com.br/).
My question is: what's the conceptual/practical difference between using a ANN + GA in a situation where i could use GA alone? I mean, is my Tetris Bot a ANN?(I don't think so).
There are several related questions about this, but i couldn't find a answer:
Are evolutionary algorithms and neural networks used in the same domains?
When to use Genetic Algorithms vs. when to use Neural Networks?
Thanks!
A genetic algorithm is an optimization algorithm.
An artificial neural network is a function approximator. In order to approximate a function you need an optimization algorithm to adjust the weights. An ANN can be used for supervised learning (classification, regression) or reinforcement learning and some can even be used for unsupervised learning.
In supervised learning a derivative-free optimization algorithm like a genetic algorithm is slower than most of the optimization algorithms that use gradient information. Thus, it only makes sense to evolve neural networks with genetic algorithms in reinforcement learning. This is known as "neuroevolution". The advantage of neural networks like multilayer perceptrons in this setup is that they can approximate any function with arbitrary precision when they have a suffficient number of hidden nodes.
When you create a tetris bot you do not necessarily have to use an ANN as a function approximator. But you need some kind of function approximator to represent your bot's policy. I guess it was just simpler than an ANN. But when you want to create a complex nonlinear policy you could do that e. g. with an ANN.
alfa's answer is perfect. Here is just an image to illustrate what he said:
Meta-Optimizer = None (but could be)
Optimizer = Genetic Algorithm
Problem = Tetris Bot (e.g. ANN)
You use evolutionary algorithm if you yet don't know the answer but you are able to somehow rate candidates and provide meaningful mutations.
Neural network is great if you already have answers (and inputs) and you want to "train the computer" so it can "guess" the answers for unknown inputs. Also, you don't have to think a lot about the problem, the network will figure it out by itself.
Check this "game AI" example: https://synaptic.juancazala.com/#/
(note how simple it is, all you have to do is to give them enough training, you don't have to know a thing about game AI - and once it is good enough all you have to do is to "download" memory and run it when needed)
I'm not an expert, but based on what I know from the field..
An artificial neural network has a basis on neuroscience ultimately. It attempts to simulate/model its behavior through building a neuron-like structures in the algorithm. There is a strong emphasis on the academic nature of the problem than the result. From what I understand, its for this reason that ANN's are not very popular from an engineering standpoint. Statistical basis of machine learning (HMM's and Bayesian networks) produce better results.
In short, so as long as it has a nod towards some underlying neurosciency subject, it can be a ANN, even if it uses some form of GA.
If you use a GA, it is not necessarily an ANN.
I have a typical AI Problem to solve. Customers gonna submit comments about a product. I have to be able to create a program that classify these comment as either good,bad or neutral.
Surely, Neural Network gonna play a great role in it.
Also, I think fuzzy logic can play some role in it. Such as how far a comment is good,bad or neutral!!
Some more ideas about how to solve it??
This problem is usually referred to as Sentiment Analysis. You can check out the wikipedia entry about Sentiment Analysis for a brief review, or Liu Bing's page on sentiment analysis for more detailed resources and tutorials.
You can use some form of supervised learning.
The most important thing for classification is then choosing the right features. "Features" means you extract some values from the review that still capture the essence with respect to the classification task. Things that come to my mind are
number of words
average number of words per sentence
number of words from some set like {crap, shit, damn, viagra, ...}
Then you can use any available machine learning algorithm (neural networks, SVM) and train a classifier given you have enough reviews that are labeled with good/neutral/bad.
Neural networks would certainly work for it, however I would be supicious about introducing new words, and languages. I would go for a Bayes net approach for determining the probability of being in a "good/neutral/bad" state. You should consider cleaning the data [stemming, etc] before putting it through the bayes net.
Additionally: The meta attributes [what ziggy mentioned] are more of an indicator to boost the performance of the approach you take.
EDIT: Bayes-Nets are a form of supervised learning.
Questions
I want to classify/categorize/cluster/group together a set of several thousand websites. There's data that we can train on, so we can do supervised learning, but it's not data that we've gathered and we're not adamant about using it -- so we're also considering unsupervised learning.
What features can I use in a machine learning algorithm to deal with multilingual data? Note that some of these languages might not have been dealt with in the Natural Language Processing field.
If I were to use an unsupervised learning algorithm, should I just partition the data by language and deal with each language differently? Different languages might have different relevant categories (or not, depending on your psycholinguistic theoretical tendencies), which might affect the decision to partition.
I was thinking of using decision trees, or maybe Support Vector Machines (SVMs) to allow for more features (from my understanding of them). This post suggests random forests instead of SVMs. Any thoughts?
Pragmatical approaches are welcome! (Theoretical ones, too, but those might be saved for later fun.)
Some context
We are trying to classify a corpus of many thousands of websites in 3 to 5 languages (maybe up to 10, but we're not sure).
We have training data in the form of hundreds of websites already classified. However, we may choose to use that data set or not -- if other categories make more sense, we're open to not using the training data that we have, since it is not something we gathered in the first place. We are on the final stages of scraping data/text from websites.
Now we must decide on the issues above. I have done some work with the Brown Corpus and the Brill tagger, but this will not work because of the multiple-languages issue.
We intend to use the Orange machine learning package.
According to the context you have provided, this is a supervised learning problem.
Therefore, you are doing classification, not clustering. If I misunderstood, please update your question to say so.
I would start with the simplest features, namely tokenize the unicode text of the pages, and use a dictionary to translate every new token to a number, and simply consider the existence of a token as a feature.
Next, I would use the simplest algorithm I can - I tend to go with Naive Bayes, but if you have an easy way to run SVM this is also nice.
Compare your results with some baseline - say assigning the most frequent class to all the pages.
Is the simplest approach good enough? If not, start iterating over algorithms and features.
If you go the supervised route, then the fact that the web pages are in multiple languages shouldn't make a difference. If you go with, say lexical features (bag-o'-words style) then each language will end up yielding disjoint sets of features, but that's okay. All of the standard algorithms will likely give comparable results, so just pick one and go with it. I agree with Yuval that Naive Bayes is a good place to start, and only if that doesn't meet your needs that try something like SVMs or random forests.
If you go the unsupervised route, though, the fact that the texts aren't all in the same language might be a big problem. Any reasonable clustering algorithm will first group the texts by language, and then within each language cluster by something like topic (if you're using content words as features). Whether that's a bug or a feature will depend entirely on why you want to classify these texts. If the point is to group documents by topic, irrespective of language, then it's no good. But if you're okay with having different categories for each language, then yeah, you've just got as many separate classification problems as you have languages.
If you do want a unified set of classes, then you'll need some way to link similar documents across languages. Are there any documents in more that one language? If so, you could use them as a kind of statistical Rosetta Stone, to link words in different languages. Then, using something like Latent Semantic Analysis, you could extend that to second-order relations: words in different languages that don't ever occur in the same document, but which tend to co-occur with words which do. Or maybe you could use something like anchor text or properties of the URLs to assign a rough classification to documents in a language-independent manner and use that as a way to get started.
But, honestly, it seems strange to go into a classification problem without a clear idea of what the classes are (or at least what would count as a good classification). Coming up with the classes is the hard part, and it's the part that'll determine whether the project is a success or failure. The actual algorithmic part is fairly rote.
Main answer is: try different approaches. Without actual testing it's very hard to predict what method will give best results. So, I'll just suggest some methods that I would try first and describe their pros and cons.
First of all, I would recommend supervised learning. Even if the data classification is not very accurate, it may still give better results than unsupervised clustering. One of the reasons for it is a number of random factors that are used during clustering. For example, k-means algorithm relies on randomly selected points when starting the process, which can lead to a very different results for different program runnings (though x-means modifications seems to normalize this behavior). Clustering will give good results only if underlying elements produce well separated areas in the feature space.
One of approaches to treating multilingual data is to use multilingual resources as support points. For example, you can index some Wikipedia's articles and create "bridges" between same topics in different languages. Alternatively, you can create multilingual association dictionary like this paper describes.
As for methods, the first thing that comes to mind is instance-based semantic methods like LSI. It uses vector space model to calculate distance between words and/or documents. In contrast to other methods it can efficiently treat synonymy and polysemy. Disadvantage of this method is a computational inefficiency and leak of implementations. One of the phases of LSI makes use of a very big cooccurrence matrix, which for large corpus of documents will require distributed computing and other special treatment. There's modification of LSA called Random Indexing which do not construct full coocurrence matrix, but you'll hardly find appropriate implementation for it. Some time ago I created library in Clojure for this method, but it is pre-alpha now, so I can't recommend using it. Nevertheless, if you decide to give it a try, you can find project 'Clinch' of a user 'faithlessfriend' on github (I'll not post direct link to avoid unnecessary advertisement).
Beyond special semantic methods the rule "simplicity first" must be used. From this point, Naive Bayes is a right point to start from. The only note here is that multinomial version of Naive Bayes is preferable: my experience tells that count of words really does matter.
SVM is a technique for classifying linearly separable data, and text data is almost always not linearly separable (at least several common words appear in any pair of documents). It doesn't mean, that SVM cannot be used for text classification - you still should try it, but results may be much lower than for other machine learning tasks.
I haven't enough experience with decision trees, but using it for efficient text classification seems strange to me. I have seen some examples where they gave excellent results, but when I tried to use C4.5 algorithm for this task, the results were terrible. I believe you should get some software where decision trees are implemented and test them by yourself. It is always better to know then to suggest.
There's much more to say on every topic, so feel free to ask more questions on specific topic.
Just wondering, since we've reached 1 teraflop per PC, yet we are still not able to model an insect's brain.
Has anyone seen a decent implementation of a self-learning, self-developing neural network?
I saw an interesting experiment mapping the physical neural layout of a rat's brain to a digital neural network with weighting modelled on the neuron chemistry of each component taken using MRI and others. Quite interesting. (new scientist or Focus, 2 issues ago?)
IBM Blue Brain comes to mind
http://news.bbc.co.uk/1/hi/sci/tech/8012496.stm
The problem is computation power as you rightly point out. But for a sequence of stimuli to a neural network the range of calculations tends to be exponential as that stimuli encounters deeper nested nodes. Any complex weighting algorithm means that time spent at each node can get expensive. Domain specific neural-maps tend to be quicker because they are specialized. Brains in mammals have many general paths, making it harder to teach them, and for a computer to model a real mammal brain in a given space/time.
Real brains also have tons of cross-talk like static (some people think this is where creativity or original thought stems from). Brains also don't learn using 'direct' stimulus/reward ... they use past experience of non-related matter to create their own learning. Recreating the neurons is one thing in a computational space, creating an accurate learning is another. Never-mind the dopamine (octopamine in insects) and other neurological chemicals.
imagine giving a digital brain LSD or anti-depressants. As a real simulation. Awesome. That would be a complex simulation I suspect.
I think you're kind of making the assumption that our idea of how neural networks work is a good model for the brain at a large-scale level; I'm not sure that is a good assumption. Hell, not too many years ago we didn't think the glial cells were important to mental functions, and it was the idea for a long time that there is no neurogenesis after the brain matures.
On the other hand, neural networks do seem to handle some apparently complex functions pretty well.
So, here's a little puzzle question for you: how many teraflops or petaflops do you think a human brain's computation represents?
Jeff Hawkins would say that a neural net is a poor approximation of a brain. His "On Intelligence" is a terrific read.
Yup: OpenCog is working on it.
It's the structure. Even if we had computers today with the same or higher performance than a human brain (there are different predictions when we'll get there, but there are still a few years to go), we still need to program it. And while we know a lot of the brain today, there are still many, many more things we do not know. And these aren't just details, but large areas that are not understood at all.
Focusing only on the Tera-/Peta-FLOPS is like looking only at megapixels with digital cameras: it focuses on only one value when there are many factors involved (and there are a few more of those in a brain than in a camera). I also believe that many of the estimates just how many FLOPS would be needed to simulate a brain are way off - but that's a different discussion altogether.
Just wondering, we've reached 1 teraflop per PC, and we are still not able to model an insect's brain. has anyone seen a decent implementation of a self-learning self-developing neural network?
We can already model brains. The question these days, is how fast, and how accurate.
In the beginning, there was effort expended on trying to find the most abstract representation of neurons with the least amount of physical properties needed.
This led to the invention of the perceptron at Cornell University, which is a very simple model indeed. In fact, it may have been too simple, as the famous MIT AI professor, Marvin Minsky, wrote a paper which mistakenly concluded that it would be impossible for this type of model to learn XOR (a basic logic gate that could be emulated by every computer we have today). Unfortunately, his paper plunged neural network research into the dark ages for at least 10 years.
While probably not as impressive as many would like, there are learning networks that are already in existence that can do visual and speech learning and recognition.
And even though we have faster CPUs, it is still not the same as a neuron. Neurons in our brain are, at the very least, parallel adder units. So imagine 100 billion simulated human neurons, adding each second, sending their outputs to 100 trillion connections with a "clock" of about 20hz. The amount of computation going on here far exceeds the petaflops of processing power we have, especially when our cpus are mostly serial instead of parallel.
In 2007, they simulated the equivalent of a half mouse brain for 10 seconds at half the actual speed: http://news.bbc.co.uk/1/hi/technology/6600965.stm
There is a worm named C. Elegance and its anatomy is completely know to us. Every cell is mapped out and every neuron is well studied. This worm has an interesting property by birth and that is it follows or grow towards only those temperature regions in which it was born. Here is link to the paper. This paper has implementation of the property with neuronal model. And there are some students who have built robot that only follows dark regions in the region having different shades of light, using this neuronal model. This work could have been done using other methods as well but this method is more noise resilient as proved by paper to which I have given link above.
I have asked other AI folk this question, but I haven't really been given an answer that satisfied me.
For anyone else that has programmed an artificial neural network before, how do you test for its correctness?
I guess, another way to put it is, how does one debug the code behind a neural network?
With neural networks, generally what is happening is you are taking an untrained neural network, and you are training it up using a given set of data, so that it responds in the way you expect. Here's the deal; usually, you're training it up to a certain confidence level for your inputs. Generally (and again, this is just generally; your mileage may vary), you cannot get neural networks to always provide the right answer; rather, you are getting the estimation of the right answer, to within a confidence range. You know that confidence range by how you have trained the network.
The question arises as to why you would want to use neural networks if you cannot be certain that the conclusion they come to is verifiably correct; the answer is that neural networks can arrive at high-confidence answers for certain classes of problems (specifically, NP-Complete problems) in linear time, whereas verifiably correct solutions of NP-Complete problems can only be arrived at in polynomial time. In layman's terms, neural networks can "solve" problems that normal computation can't; but you can only be a certain percentage confident that you have the right answer. You can determine that confidence by the training regimen, and can usually make sure that you will have at least 99.9% confidence.
Correctness is a funny concept in most of "soft computing." The best I can tell you is: "a neural network is correct when it consistently satisfies the parameters of it's design." You do this by training it with data, and then verifying with other data, and having a feedback loop in the middle which lets you know if the neural network is functioning appropriately.
This is of-course the case only for neural networks that are large enough where a direct proof of correctness is not possible. It is possible to prove that a neural network is correct through analysis if you are attempting to build a neural network that learns XOR or something similar, but for that class of problem an aNN is seldom necessary.
You're opening up a bigger can of worms here than you might expect.
NN's are perhaps best thought of as universal function approximators, by the way, which may help you in thinking about this stuff.
Anyway, there is nothing special about NN's in terms of your question, the problem applies to any sort of learning algorithm.
The confidence you have in the results it is giving is going to rely on both the quantity and the quality (often harder to determine) of the training data that you have.
If you're really interested in this stuff, you may want to read up a bit on the problems of overtraining, and ensemble methods (bagging, boosting, etc.).
The real problem is that you usually aren't actually interested in the "correctness" (cf quality) of an answer on a given input that you've already seen, rather you care about predicting the quality of answer on an input you haven't seen yet. This is a much more difficult problem. Typical approaches then, involve "holding back" some of your training data (i.e. the stuff you know the "correct" answer for) and testing your trained system against that. It gets subtle though, when you start considering that you may not have enough data, or it may be biased, etc. So there are many researchers who basically spend all of their time thinking about these sort of issues!
I've worked on projects where there is test data as well as training data, so you know the expected outputs for a set of inputs the NN hasn't seen.
One common way of analysing the result of any classifier is use of an ROC curve; an introduction to the statistics of classifiers and ROC curves can be found at Interpreting Diagnostic Tests
I'm a complete amateur in this field, but don't you use a pre-determined set of data you know is correct?
I don't believe there is a single correct answer but there are well-proven probabilistic or statistical methods that can provide reassurance. The statistical methods are usually referred to as Resampling.
One method that I can recommend is the Jackknife.
My teacher always said his rule of thumb was to train the NN with 80% of your data and validate it with the other 20%. And, of course, make sure that data set is as comprehensive as you need.
If you want to find out whether the backpropagation of the network is correct, there is an easy way.
Since you calculate the derivate of the error landscape, you can check whether your implementation is correct numerically. You will calculate the derivative of the error with respect to a specific weight, ∂E/∂w. You can show that
∂E/∂w = (E(w + e) - E(w - e)) / (2 * e) + O(e^2).
(Bishop, Machine Learning and Pattern Recognition, p. 246)
Essentially, you evaluate the error to the left of the weight, evaluate it to the right of the weight and chheck if the numerical gradient is the same as your analytical gradient.
(Here's an implementation: http://github.com/bayerj/arac/raw/9f5b225d6293974f8adfc5f20dfc6439cc1bed35/src/cpp/utilities/utilities.cpp)
To me probably there is only one value(s) takes extra effort to verify, the gradient of the back propagation. I think Bayer's answer is actually commonly used and suggested. You need to write extra code to this but all are forward propagation matrix multiplications which is easy to write and verify.
There are some other issues which will prevent you from getting the best answer, for example:
The cost function of NN is not concave so your gradient descent is not guaranteed to find the global optimum.
Over/under fitting
Not choosing the "right" features/model
etc
However I think they are beyond the scope of programming bug.