I'm implementing AdaBoost(Boosting) that will use CART and C4.5. I read about AdaBoost, but i can't find good explenation how to join AdaBoost with Decision Trees. Let say i have data set D that have n examples. I split D to TR training examples and TE testing examples.
Let say TR.count = m,
so i set weights that should be 1/m, then i use TR to build tree, i test it with TR to get wrong examples, and test with TE to calculate error. Then i change weights, and now how i will get next Training Set? What kind of sampling should i use (with or without replacemnet)? I know that new Training Set should focus more on samples that were wrong classified but how can i achieve this? Well how CART or C4.5 will know that they should focus on examples with greater weight?
As I know, the TE data sets don't mean to be used to estimate the error rate. The raw data can be split into two parts (one for training, the other for cross validation). Mainly, we have two methods to apply weights on the training data sets distribution. Which method to use is determined by the weak learner you choose.
How to apply the weights?
Re-sample the training data sets without replacement. This method can be viewed as weighted boosting method. The generated re-sampling data sets contain miss-classification instances with higher probability than the correctly classified ones, therefore it force the weak learning algorithm to concentrate on the miss-classified data.
Directly use the weights when learning. Those models include Bayesian Classification, Decision Tree (C4.5 and CART) and so on. With respect to C4.5, we calculate the the gain information (mutation information) to determinate which predictor will be selected as the next node. Hence we can combine the weights and entropy to estimate the measurements. For example, we view the weights as the probability of the sample in the distribution. Given X = [1,2,3,3], weights [3/8,1/16,3/16,6/16 ]. Normally, the cross-entropy of X is (-0.25log(0.25)-0.25log(0.25)-0.5log(0.5)), but with weights taken into consideration, its weighted cross-entropy is (-(3/8)log(3/8)-(1/16)log(1/16)-(9/16log(9/16))). Generally, the C4.5 can be implemented by weighted cross-entropy, and its weight is [1,1,...,1]/N.
If you want to implement the AdaboostM.1 with C4.5 algorithmsm you should read some stuff in Page 339, the Elements of Statistical Learning.
Related
I'm working on knowledge graph, more precisely in natural language processing field. To evaluate the components of my algorithm, it is necessary to be able to classify the good and the poor candidates. For this purpose, we manually classified pairs in a dataset.
My system returns the relevant pairs according to the implementation logic. now I'm able to calculate :
Precision = X
Recall = Y
For establishing a complete curve I need the rest of points (X,Y), what should I do?:
build another dataset for test ?
split my dataset ?
or any other solution ?
Neither of your proposed two methods. In short, Precision-recall or ROC curve is designed for classifiers with probabilistic output. That is, instead of simply producing a 0 or 1 (in case of binary classification), you need classifiers that can provide a probability in [0,1] range. This is the function to do it in sklearn, note how the 2nd parameter is called probas_pred.
To turn this probabilities into concrete class prediction, you can then set a threshold, say at .5. Setting such a threshold is problematic however, since you can trade-off precision/recall by varying the threshold, and an arbitrary choice can give false impression of a classifier's performance. To circumvent this, threshold-independent measures like area under ROC or Precision-Recall curve is used. They create thresholds at different intervals, say 0.1,0.2,0.3...0.9, turn probabilities into binary classes and then compute precision-recall for each such threshold.
I came across class center based fuzzification algorithm on page 16 of this research paper on TRFDT. However, I fail to understand what is happening in step 2 of this algorithm (titled in the paper as Algorithm 2: Fuzzification). If someone could explain it by giving a small example it would certainly be helpful.
It is not clear from your question which parts of the article you understand and IMHO the article is written in not the clearest possible way, so this is going to be a long answer.
Let's start with some intuition behind this article. In short I'd say it is: "let's add fuzziness everywhere to decision trees".
How a decision tree works? We have a classification problem and we say that instead of analyzing all attributes of a data point in a holistic way, we'll analyze them one by one in an order defined by the tree and will navigate the tree until we reach some leaf node. The label at that leaf node is our prediction. So the trick is how to build a good tree i.e. a good order of attributes and good splitting points. This is a well studied problem and the idea is to build a tree that encode as much information as possible by some metric. There are several metrics and this article uses entropy which is similar to widely used information gain.
The next idea is that we can change the classification (i.e. split of the values into a classes) as fuzzy rather than exact (aka "crisp"). The idea here is that in many real life situations not all members of the class are equally representative: some a more "core" examples and some a more "edge" example. If we can catch this difference, we can provide a better classification.
And finally there is a question of how similar the data points are (generally or by some subset of attributes) and here we can also have a fuzzy answer (see formulas 6-8).
So the idea of the main algorithm (Algorithm 1) is the same as in the ID3 tree: recursively find the attribute a* that classifies the data in the best way and perform the best split along that attribute. The main difference is in how the information gain for the best attribute selection is measured (see heuristic in formulas 20-24) and that because of fuzziness the usual stop rule of "only one class left" doesn't work anymore and thus another entropy (Kosko fuzzy entropy in 25) is used to decide if it is time to stop.
Given this skeleton of the algorithm 1 there are quite a few parts that you can (or should) select:
How do you measure μ(ai)τ(Cj)(x) used in (20) (this is a measure of how well x represents the class Cj with respect to attribute ai, note that here being not in Cj and far from the points in Cj is also good) with two obvious choices of the lower (16 and 18) and the upper bounds (17 and 19)
How do you measure μRτ(x, y) used in (16-19). Given that R is induced by ai this becomes μ(ai)τ(x, y) which is a measure of similarity between two points with respect to attribute ai. Here you can choose one of the metrics (6-8)
How do you measure μCi(y) used in (16-19). This is the measure of how well the point y fits in the class Ci. If you already have data as fuzzy classification, there is nothing you should do here. But if your input classification is crisp, then you should somehow produce μCi(y) from that and this is what the Algorithm 2 does.
There is a trivial solution of μCj(xi) = "1 if xi ∈ Cj and 0 otherwise" but this is not fuzzy at all. The process of building fuzzy data is called "fuzzification". The idea behind the Algorithm 2 is that we assume that every class Cj is actually some kind of a cluster in the space of attributes. And so we can measure the degree of membership μCj(xi) as the distance from the xi to the center of the cluster cj (the closer we are, the higher the membership should be so it is really some inverse of a distance). Note that since distance is measured by attributes, you should normalize your attributes somehow or one of them might dominate the distance. And this is exactly what the Algorithm 2 does:
it estimates the center of the cluster for class Cj as the center of mass of all the known points in that class i.e. just an average of all points by each coordinate (attribute).
it calculates the distances from each point xi to each estimated center of class cj
looking into formula at step #12 it uses inverse square of the distance as a measure of proximity and just normalizes the value because for fuzzy sets Sum[over all Cj](μCj(xi)) should be 1
I am trying to handle a data set on matlab with 3 classes and negative and positive values on attributes. I tried naive bayes classifier but matlab says tha naive bayes can't handle negative values. Svm algorithm also can't handle this problem because there are 3 classes. So, i am asking you which algorithm to chose?
Thank you in advance!!
The simples solution that comes to mind is a k-NN classifier using majority voting. Say you want to classify a point and you use 10 nearest neighbours. Let's say that six out of 10 are class 1, two neighbours are class 2 and the two remaining neighbours are class 3, so in this case you would classify your point as class 1.
If you want to include nonlinearity (as in the case of SVM) you can use nonlinear kernels in k-NN too which basically means modifying the distance calculation.
citing wikipedia:
Multiclass SVM[edit]Multiclass SVM aims to assign labels to instances by using support vector machines, where the labels are drawn from a finite set of several elements.
The dominant approach for doing so is to reduce the single multiclass problem into multiple binary classification problems.[8] Common methods for such reduction include:[8] [9]
Building binary classifiers which distinguish between (i) one of the labels and the rest (one-versus-all) or (ii) between every pair of classes (one-versus-one). Classification of new instances for the one-versus-all case is done by a winner-takes-all strategy, in which the classifier with the highest output function assigns the class (it is important that the output functions be calibrated to produce comparable scores). For the one-versus-one approach, classification is done by a max-wins voting strategy, in which every classifier assigns the instance to one of the two classes, then the vote for the assigned class is increased by one vote, and finally the class with the most votes determines the instance classification.
Directed Acyclic Graph SVM (DAGSVM)[10]
error-correcting output codes[11]
Crammer and Singer proposed a multiclass SVM method which casts the multiclass classification problem into a single optimization problem, rather than decomposing it into multiple binary classification problems.[12] See also Lee, Lin and Wahba.[13][14]
For a homework assignment I need to fit several classification models to a data set and compare their lift charts to determine the most effective model. The models produce a binary result (or a probability of that binary result), lets call them YES or NO. Models with continuous output are easy to generate lift charts for as its easy to order the data set in descending order of confidence.
I am having trouble doing that with models that generate a binary result (k-NN and ClassificationTree) for example. In my head I know methods to create a confidence value but I don't know how to do it with these libraries.
For k-NN I would set the probability confidence to the probability of a YES in the training data that falls through a particular path in the tree. However with this method, and the tree model in MATLAB, I don't know which tree path each record falls through.
Similarly with k-NN I would take the probability based upon the k neighbors, and find the probability of a YES from those k neighbors, but the model doesn't tell me the k neighbors and I'd prefer to not do a search for them.
Any help with one or both of these problems (or a better way of producing lift charts in MATLAB is greatly appreciated)
I was actually able to find the answer to my own question. The predict function in MATLAB produces scores for the probability of each type of class in the prediction model
[class, score] = predict(mdl, new_observation);
Hey everyone, I've been trying to get an ANN I coded to work with the backpropagation algorithm. I have read several papers on them, but I'm noticing a few discrepancies.
Here seems to be the super general format of the algorithm:
Give input
Get output
Calculate error
Calculate change in weights
Repeat steps 3 and 4 until we reach the input level
But here's the problem: The weights need to be updated at some point, obviously. However, because we're back propagating, we need to use the weights of previous layers (ones closer to the output layer, I mean) when calculating the error for layers closer to the input layer. But we already calculated the weight changes for the layers closer to the output layer! So, when we use these weights to calculate the error for layers closer to the input, do we use their old values, or their "updated values"?
In other words, if we were to put the the step of updating the weights in my super general algorithm, would it be:
(Updating the weights immediately)
Give input
Get output
Calculate error
Calculate change in weights
Update these weights
Repeat steps 3,4,5 until we reach the input level
OR
(Using the "old" values of the weights)
Give input
Get output
Calculate error
Calculate change in weights
Store these changes in a matrix, but don't change these weights yet
Repeat steps 3,4,5 until we reach the input level
Update the weights all at once using our stored values
In this paper I read, in both abstract examples (the ones based on figures 3.3 and 3.4), they say to use the old values, not to immediately update the values. However, in their "worked example 3.1", they use the new values (even though what they say they're using are the old values) for calculating the error of the hidden layer.
Also, in my book "Introduction to Machine Learning by Ethem Alpaydin", though there is a lot of abstract stuff I don't yet understand, he says "Note that the change in the first-layer weight delta-w_hj, makes use of the second layer weight v_h. Therefore, we should calculate the changes in both layers and update the first-layer weights, making use of the old value of the second-layer weights, then update the second-layer weights."
To be honest, it really seems like they just made a mistake and all the weights are updated simultaneously at the end, but I want to be sure. My ANN is giving me strange results, and I want to be positive that this isn't the cause.
Anyone know?
Thanks!
As far as I know, you should update weights immediately. The purpose of back-propagation is to find weights that minimize the error of the ANN, and it does so by doing a gradient descent. I think the algorithm description in the Wikipedia page is quite good. You may also double-check its implementation in the joone engine.
You are usually backpropagating deltas not errors. These deltas are calculated from the errors, but they do not mean the same thing. Once you have the deltas for layer n (counting from input to output) you use these deltas and the weigths from the layer n to calculate the deltas for layer n-1 (one closer to input). The deltas only have a meaning for the old state of the network, not for the new state, so you should always use the old weights for propagating the deltas back to the input.
Deltas mean in a sense how much each part of the NN has contributed to the error before, not how much it will contribute to the error in the next step (because you do not know the actual error yet).
As with most machine-learning techniques it will probably still work, if you use the updated, weights, but it might converge slower.
If you simply train it on a single input-output pair my intuition would be to update weights immediately, because the gradient is not constant. But I don't think your book mentions only a single input-output pair. Usually you come up with an ANN because you have many input-output samples from a function you would like to model with the ANN. Thus your loops should repeat from step 1 instead of from step 3.
If we label your two methods as new->online and old->offline, then we have two algorithms.
The online algorithm is good when you don't know how many sample input-output relations you are going to see, and you don't mind some randomness in they way the weights update.
The offline algorithm is good if you want to fit a particular set of data optimally. To avoid overfitting the samples in your data set, you can split it into a training set and a test set. You use the training set to update the weights, and the test set to measure how good a fit you have. When the error on the test set begins to increase, you are done.
Which algorithm is best depends on the purpose of using an ANN. Since you talk about training until you "reach input level", I assume you train until output is exactly as the target value in the data set. In this case the offline algorithm is what you need. If you were building a backgammon playing program, the online algorithm would be a better because you have an unlimited data set.
In this book, the author talks about how the whole point of the backpropagation algorithm is that it allows you to efficiently compute all the weights in one go. In other words, using the "old values" is efficient. Using the new values is more computationally expensive, and so that's why people use the "old values" to update the weights.