Is Latent Semantic Indexing (LSI) a Statistical Classification algorithm? Why or why not?
Basically, I'm trying to figure out why the Wikipedia page for Statistical Classification does not mention LSI. I'm just getting into this stuff and I'm trying to see how all the different approaches for classifying something relate to one another.
No, they're not quite the same. Statistical classification is intended to separate items into categories as cleanly as possible -- to make a clean decision about whether item X is more like the items in group A or group B, for example.
LSI is intended to show the degree to which items are similar or different and, primarily, find items that show a degree of similarity to an specified item. While this is similar, it's not quite the same.
LSI/LSA is eventually a technique for dimensionality reduction, and usually is coupled with a nearest neighbor algorithm to make it a into classification system. Hence in itself, its only a way of "indexing" the data in lower dimension using SVD.
Have you read about LSI on Wikipedia ? It says it uses matrix factorization (SVD), which in turn is sometimes used in classification.
The primary distinction in machine learning is between "supervised" and "unsupervised" modeling.
Usually the words "statistical classification" refer to supervised models, but not always.
With supervised methods the training set contains a "ground-truth" label that you build a model to predict. When you evaluate the model, the goal is to predict the best guess at (or probability distribution of) the true label, which you will not have at time of evaluation. Often there's a performance metric and it's quite clear what the right vs wrong answer is.
Unsupervised classification methods attempt to cluster a large number of data points which may appear to vary in complicated ways into a smaller number of "similar" categories. Data in each category ought to be similar in some kind of 'interesting' or 'deep' way. Since there is no "ground truth" you can't evaluate 'right or wrong', but 'more' vs 'less' interesting or useful.
Similarly evaluation time you can place new examples into potentially one of the clusters (crisp classification) or give some kind of weighting quantifying how similar or different looks like the "archetype" of the cluster.
So in some ways supervised and unsupervised models can yield something which is a "prediction", prediction of class/cluster label, but they are intrinsically different.
Often the goal of an unsupervised model is to provide more intelligent and powerfully compact inputs for a subsequent supervised model.
Related
Are there any internal validity indices/methods to evaluate the quality of my algorithm, which don't mostly depend on the proximity measure (e.g., distance matrix)?
All the conventional measures (such as: silhouette, Dunn index, N-cut, DB index, etc.) depends on how well you defined a proximity over the data and on the final partition, rather the data itself.
There is no such thing as "depending on the data itself", data is an abstract term which can describe set of elephants or rings isomorphisms. In order to define any index you need to use one of two things:
In supervised scenario (when you know some class of objects, not neceserly use it for trianing, but you have to know them) you can use these labels to calculate impurity, or any other classification derived score
in unsupervised scenario you have to use some similarity measure, which can be very arbitrary, it might be an inverse of some metric, but it might be completely abstract measure derived from asking some people "are these element similar?", it might consists elements that are not comparable ("nans" in the matrix), it might be not symmetric, but some similarity measure is crucial, there is no "magical", "deep" meaning "in the data". You may extract similarity measure from some different models (like generative models, autoencoders etc.) but it is still the same conceptually, simply instead of giving the rules by hand, you give an algorithm by hand which extracts the rules.
To sum up. You cannot evaluate a clustering as such, you can only evaluate how well it works for a particular task, and this task can be:
some bigger problem, where clustering is just one of the steps and you plug your clustering and observe change in the whole system's quality
optimization of some class-based criterion (supervised)
optimization of some similarity/distance based criterion (unsupervised)
There are no more options. Unsupervised learning is not a real, well posed problem, this is only a tool to simplify some real problems. As a result you won't ever be able to say "this clustering is good", you might only say that "this clustering is good in task A,B,C under assumption of pipelines X,Y,Z"
I'm looking for a supervised machine learning algorithm that would produce transparent rules or definitions that can be easily interpreted by a human.
Most algorithms that I work with (SVMs, random forests, PLS-DA) are not very transparent. That is, you can hardly summarize the models in a table in a publication aimed at a non-computer scientist audience. What authors usually do is, for example, publish a list of variables that are important based on some criterion (for example, Gini index or mean decrease of accuracy in the case of RF), and sometimes improve this list by indicating how these variables differ between the classes in question.
What I am looking is a relatively simple output of the style "if (any of the variables V1-V10 > median or any of the variables V11-V20 < 1st quartile) and variable V21-V30 > 3rd quartile, then class A".
Is there any such thing around?
Just to constraint my question a bit: I am working with highly multidimensional data sets (tens of thousands to hundreds of thousands of often colinear variables). So for example regression trees would not be a good idea (I think).
You sound like you are describing decision trees. Why would regression trees not be a good choice? Maybe not optimal, but they work, and those are the most directly interpretable models. Anything that works on continuous values works on ordinal values.
There's a tension between wanting an accurate classifier, and wanting a simple and explainable model. You could build a random decision forest model, and constrain it in several ways to make it more interpretable:
Small max depth
High minimum information gain
Prune the tree
Only train on "understandable" features
Quantize/round decision threhsolds
The model won't be as good, necessarily.
You can find interesting research in the understanding AI methods done by Been Kim at Google Brain.
How do you find an optimum learning rule for a given problem, say a multiple category classification?
I was thinking of using Genetic Algorithms, but I know there are issues surrounding performance. I am looking for real world examples where you have not used the textbook learning rules, and how you found those learning rules.
Nice question BTW.
classification algorithms can be classified using many Characteristics like:
What does the algorithm strongly prefer (or what type of data that is most suitable for this algorithm).
training overhead. (does it take a lot of time to be trained)
When is it effective. ( large data - medium data - small amount of data ).
the complexity of analyses it can deliver.
Therefore, for your problem classifying multiple categories I will use Online Logistic Regression (FROM SGD) because it's perfect with small to medium data size (less than tens of millions of training examples) and it's really fast.
Another Example:
let's say that you have to classify a large amount of text data. then Naive Bayes is your baby. because it strongly prefers text analysis. even that SVM and SGD are faster, and as I experienced easier to train. but these rules "SVM and SGD" can be applied when the data size is considered as medium or small and not large.
In general any data mining person will ask him self the four afomentioned points when he wants to start any ML or Simple mining project.
After that you have to measure its AUC, or any relevant, to see what have you done. because you might use more than just one classifier in one project. or sometimes when you think that you have found your perfect classifier, the results appear to be not good using some measurement techniques. so you'll start to check your questions again to find where you went wrong.
Hope that I helped.
When you input a vector x to the net, the net will give an output depend on all the weights (vector w). There would be an error between the output and the true answer. The average error (e) is a function of the w, let's say e = F(w). Suppose you have one-layer-two-dimension network, then the image of F may look like this:
When we talk about training, we are actually talking about finding the w which makes the minimal e. In another word, we are searching the minimum of a function. To train is to search.
So, you question is how to choose the method to search. My suggestion would be: It depends on how the surface of F(w) looks like. The wavier it is, the more randomized method should be used, because the simple method based on gradient descending would have bigger chance to guide you trapped by a local minimum - so you lose the chance to find the global minimum. On the another side, if the suface of F(w) looks like a big pit, then forget the genetic algorithm. A simple back propagation or anything based on gradient descending would be very good in this case.
You may ask that how can I know how the surface look like? That's a skill of experience. Or you might want to randomly sample some w, and calculate F(w) to get an intuitive view of the surface.
Background
Here is the problem:
A black box outputs a new number each day.
Those numbers have been recorded for a period of time.
Detect when a new number from the black box falls outside the pattern of numbers established over the time period.
The numbers are integers, and the time period is a year.
Question
What algorithm will identify a pattern in the numbers?
The pattern might be simple, like always ascending or always descending, or the numbers might fall within a narrow range, and so forth.
Ideas
I have some ideas, but am uncertain as to the best approach, or what solutions already exist:
Machine learning algorithms?
Neural network?
Classify normal and abnormal numbers?
Statistical analysis?
Cluster your data.
If you don't know how many modes your data will have, use something like a Gaussian Mixture Model (GMM) along with a scoring function (e.g., Bayesian Information Criterion (BIC)) so you can automatically detect the likely number of clusters in your data. I recommend this instead of k-means if you have no idea what value k is likely to be. Once you've constructed a GMM for you data for the past year, given a new datapoint x, you can calculate the probability that it was generated by any one of the clusters (modeled by a Gaussian in the GMM). If your new data point has low probability of being generated by any one of your clusters, it is very likely a true outlier.
If this sounds a little too involved, you will be happy to know that the entire GMM + BIC procedure for automatic cluster identification has been implemented for you in the excellent MCLUST package for R. I have used it several times to great success for such problems.
Not only will it allow you to identify outliers, you will have the ability to put a p-value on a point being an outlier if you need this capability (or want it) at some point.
You could try line fitting prediction using linear regression and see how it goes, it would be fairly easy to implement in your language of choice.
After you fitted a line to your data, you could calculate the mean standard deviation along the line.
If the novel point is on the trend line +- the standard deviation, it should not be regarded as an abnormality.
PCA is an other technique that comes to mind, when dealing with this type of data.
You could also look in to unsuperviced learning. This is a machine learning technique that can be used to detect differences in larger data sets.
Sounds like a fun problem! Good luck
There is little magic in all the techniques you mention. I believe you should first try to narrow the typical abnormalities you may encounter, it helps keeping things simple.
Then, you may want to compute derived quantities relevant to those features. For instance: "I want to detect numbers changing abruptly direction" => compute u_{n+1} - u_n, and expect it to have constant sign, or fall in some range. You may want to keep this flexible, and allow your code design to be extensible (Strategy pattern may be worth looking at if you do OOP)
Then, when you have some derived quantities of interest, you do statistical analysis on them. For instance, for a derived quantity A, you assume it should have some distribution P(a, b) (uniform([a, b]), or Beta(a, b), possibly more complex), you put a priori laws on a, b and you ajust them based on successive information. Then, the posterior likelihood of the info provided by the last point added should give you some insight about it being normal or not. Relative entropy between posterior and prior law at each step is a good thing to monitor too. Consult a book on Bayesian methods for more info.
I see little point in complex traditional machine learning stuff (perceptron layers or SVM to cite only them) if you want to detect outliers. These methods work great when classifying data which is known to be reasonably clean.
I'm working on Markov Chains and I would like to know of efficient algorithms for constructing probabilistic transition matrices (of order n), given a text file as input.
I am not after one algorithm, but I'd rather like to build a list of such algorithms. Papers on such algorithms are also more than welcome, as any tips on terminology, etc. Notice that this topic bears a strong resemblance with n-gram identification algorithms.
Any help would be much appreciated.
It sounds like there are two possible questions, you should clarify which one:
The 'text file' contains probability values and "n" and you build the matrix directly, but how to code it? This question is trivial, so let's disregard it
The 'text file' contains something like signal data and you want to model it as a Markov Chain.
'Markov Chain' generally refers to a first order stochastic process, so I'm not sure then what you mean by "order", probably the size of the matrix, but that is not typical terminology. Anyway, for 1st-order, n x n matrix, discrete time random process, you should look at Viterbi Algorithm: http://en.wikipedia.org/wiki/Viterbi_algorithm
Whenever dealing with Markov Models, I tend to end up looking at crm114 Discriminator. One, he goes into great detail about what different models there actually are (Markov isn't always the best, depending on what the application is) and provides general links and lots of background information on how probabilistic models work. While crm114 is generally used as some sort of SPAM identification tool, it is actually a more generic probability engine that I have used in other applications.