I read somewhere that is should be which.is.max of the nnet model. Is there a rule of thumb to define the value for Size ?
Unfortunately, a single appropriate size hyperparameter does not exist. This value (as well as weight decay) depends on the data and the application at hand. Cross-validation procedures may provide you with decent values for a specific dataset. You should try Random search or Grid Search, which are two basic (yet effective) approaches to this problem. I also recommend you to check this thread about how to choose the number of hidden layers and nodes in a feedforward neural network.
Related
i have quick simple question about neuron network. As we all know, it is better to make the network deeper instead of wider. So what will happen if i set each hidden layer to be just one neuron and expand my network really deep?
This question is raised because i had a lecture about CNN today. The reason why we use CNN is that we want to extract the features of images and decrease the dimensions of the input data. Since we keep making the input for each layer smaller and smaller, why not just use one neuron and make network deeper? Or something bad will happen?
thanks!
Obviously, the single-neuron example doesn't work -- otherwise, that's what we'd use.
The kernels of each layer in a CNN harness spatial relationships and evaluate those juxtapositions with non-linear functions, which are the main differentiation of a CNN over a simple linear-combination NN. Without those non-linear operations, the CNN layers are merely a programming convenience.
If you immediately collapse your input to a single value, you have a huge problem in trying to write the cascading non-linearities that comprise the output evaluation. Yes, it's theoretically possible to write a function with, say, 28x28x3 inputs and exactly the output you want -- and to train the multitiude of parameters in that function -- but it's very messy to code and nearly impossible to maintain.
For instance, imagine trying to code an entire income tax form in a single function, such that the input was the entire range of applicable monetary amounts, Boolean status info, scalar arguments (e.g. how many children are live at home), ... and have the output be the correct amount of your payment or refund. There are many Boolean equations to apply, step functions with changing tax rates, various categories of additional tax or relief, etc.
Now, parameterize all of the constant coefficients in that massive calculation. Get some 10^6 real-life observations, and train your model on only that input and labels (tax/refund amount). You don't get any intermediate results to check, only that final amount.
It's possible, but not easy to write, debug, or maintain.
I am currently using Mallet for training a sequential model using CRF. I have understood how to provide features (that solely depend on input sequence) to the mallet package. Based on my understanding, in mallet, we have to compute all the values of the feature functions (upfront). Now, I would like to use indicator functions that depend on the label of a token. The value of these functions depends on the output label sequence and during training, I can compute the values of these indicator functions as the output label sequence is known. But, when I am applying this trained CRF model on a new input (whose output label sequene is unknown), how should I calculate the values for such features.
It will be very helpful to me if anyone can provide me any tips/relevant documents.
As you've phrased it, the question doesn't make sense: if you don't know the hidden labels, you can't set anything based on those unknown labels. An example might help.
You may not need to explicitly record these relationships. At training time the algorithm sets the parameters of the CRF to represent the relationship between the observed features and the unobserved state. Different CRF architectures can allow you to add dependencies between multiple hidden states.
I'm trying to create a sample neural network that can be used for credit scoring. Since this is a complicated structure for me, i'm trying to learn them small first.
I created a network using back propagation - input layer (2 nodes), 1 hidden layer (2 nodes +1 bias), output layer (1 node), which makes use of sigmoid as activation function for all layers. I'm trying to test it first using a^2+b2^2=c^2 which means my input would be a and b, and the target output would be c.
My problem is that my input and target output values are real numbers which can range from (-/infty, +/infty). So when I'm passing these values to my network, my error function would be something like (target- network output). Would that be correct or accurate? In the sense that I'm getting the difference between the network output (which is ranged from 0 to 1) and the target output (which is a large number).
I've read that the solution would be to normalise first, but I'm not really sure how to do this. Should i normalise both the input and target output values before feeding them to the network? What normalisation function is best to use cause I read different methods in normalising. After getting the optimized weights and use them to test some data, Im getting an output value between 0 and 1 because of the sigmoid function. Should i revert the computed values to the un-normalized/original form/value? Or should i only normalise the target output and not the input values? This really got me stuck for weeks as I'm not getting the desired outcome and not sure how to incorporate the normalisation idea in my training algorithm and testing..
Thank you very much!!
So to answer your questions :
Sigmoid function is squashing its input to interval (0, 1). It's usually useful in classification task because you can interpret its output as a probability of a certain class. Your network performes regression task (you need to approximate real valued function) - so it's better to set a linear function as an activation from your last hidden layer (in your case also first :) ).
I would advise you not to use sigmoid function as an activation function in your hidden layers. It's much better to use tanh or relu nolinearities. The detailed explaination (as well as some useful tips if you want to keep sigmoid as your activation) might be found here.
It's also important to understand that architecture of your network is not suitable for a task which you are trying to solve. You can learn a little bit of what different networks might learn here.
In case of normalization : the main reason why you should normalize your data is to not giving any spourius prior knowledge to your network. Consider two variables : age and income. First one varies from e.g. 5 to 90. Second one varies from e.g. 1000 to 100000. The mean absolute value is much bigger for income than for age so due to linear tranformations in your model - ANN is treating income as more important at the beginning of your training (because of random initialization). Now consider that you are trying to solve a task where you need to classify if a person given has grey hair :) Is income truly more important variable for this task?
There are a lot of rules of thumb on how you should normalize your input data. One is to squash all inputs to [0, 1] interval. Another is to make every variable to have mean = 0 and sd = 1. I usually use second method when the distribiution of a given variable is similiar to Normal Distribiution and first - in other cases.
When it comes to normalize the output it's usually also useful to normalize it when you are solving regression task (especially in multiple regression case) but it's not so crucial as in input case.
You should remember to keep parameters needed to restore the original size of your inputs and outputs. You should also remember to compute them only on a training set and apply it on both training, test and validation sets.
I have used the ELKI implementation of DBSCAN to identify fire hot spot clusters from a fire data set and the results look quite good. The data set is spatial and the clusters are based on latitude, longitude. Basically, the DBSCAN parameters identify hot spot regions where there is a high concentration of fire points (defined by density). These are the fire hot spot regions.
My question is, after experimenting with several different parameters and finding a pair that gives a reasonable clustering result, how does one validate the clusters?
Is there a suitable formal validation method for my use case? Or is this subjective depending on the application domain?
ELKI contains a number of evaluation functions for clusterings.
Use the -evaluator parameter to enable them, from the evaluation.clustering.internal package.
Some of them will not automatically run because they have quadratic runtime cost - probably more than your clustering algorithm.
I do not trust these measures. They are designed for particular clustering algorithms; and are mostly useful for deciding the k parameter of k-means; not much more than that. If you blindly go by these measures, you end up with useless results most of the time. Also, these measures do not work with noise, with either of the strategies we tried.
The cheapest are the label-based evaluators. These will automatically run, but apparently your data does not have labels (or they are numeric, in which case you need to set the -parser.labelindex parameter accordingly). Personally, I prefer the Adjusted Rand Index to compare the similarity of two clusterings. All of these indexes are sensitive to noise so they don't work too well with DBSCAN, unless your reference has the same concept of noise as DBSCAN.
If you can afford it, a "subjective" evaluation is always best.
You want to solve a problem, not a number. That is the whole point of "data science", being problem oriented and solving the problem, not obsessed with minimizing some random quality number. If the results don't work in reality, you failed.
There are different methods to validate a DBSCAN clustering output. Generally we can distinguish between internal and external indices, depending if you have labeled data available or not. For DBSCAN there is a great internal validation indice called DBCV.
External Indices:
If you have some labeled data, external indices are great and can demonstrate how well the cluster did vs. the labeled data. One example indice is the RAND indice.https://en.wikipedia.org/wiki/Rand_index
Internal Indices:
If you don't have labeled data, then internal indices can be used to give the clustering result a score. In general the indices calculate the distance of points within the cluster and to other clusters and try to give you a score based on the compactness (how close are the points to each other in a cluster?) and
separability (how much distance is between the clusters?).
For DBSCAN, there is one great internal validation indice called DBCV by Moulavi et al. Paper is available here: https://epubs.siam.org/doi/pdf/10.1137/1.9781611973440.96
Python package: https://github.com/christopherjenness/DBCV
I have a dataset of n data, where each data is represented by a set of extracted features. Generally, the clustering algorithms need that all input data have the same dimensions (the same number of features), that is, the input data X is a n*d matrix of n data points each of which has d features.
In my case, I've previously extracted some features from my data but the number of extracted features for each data is most likely to be different (I mean, I have a dataset X where data points have not the same number of features).
Is there any way to adapt them, in order to cluster them using some common clustering algorithms requiring data to be of the same dimensions.
Thanks
Sounds like the problem you have is that it's a 'sparse' data set. There are generally two options.
Reduce the dimensionality of the input data set using multi-dimensional scaling techniques. For example Sparse SVD (e.g. Lanczos algorithm) or sparse PCA. Then apply traditional clustering on the dense lower dimensional outputs.
Directly apply a sparse clustering algorithm, such as sparse k-mean. Note you can probably find a PDF of this paper if you look hard enough online (try scholar.google.com).
[Updated after problem clarification]
In the problem, a handwritten word is analyzed visually for connected components (lines). For each component, a fixed number of multi-dimensional features is extracted. We need to cluster the words, each of which may have one or more connected components.
Suggested solution:
Classify the connected components first, into 1000(*) unique component classifications. Then classify the words against the classified components they contain (a sparse problem described above).
*Note, the exact number of component classifications you choose doesn't really matter as long as it's high enough as the MDS analysis will reduce them to the essential 'orthogonal' classifications.
There are also clustering algorithms such as DBSCAN that in fact do not care about your data. All this algorithm needs is a distance function. So if you can specify a distance function for your features, then you can use DBSCAN (or OPTICS, which is an extension of DBSCAN, that doesn't need the epsilon parameter).
So the key question here is how you want to compare your features. This doesn't have much to do with clustering, and is highly domain dependant. If your features are e.g. word occurrences, Cosine distance is a good choice (using 0s for non-present features). But if you e.g. have a set of SIFT keypoints extracted from a picture, there is no obvious way to relate the different features with each other efficiently, as there is no order to the features (so one could compare the first keypoint with the first keypoint etc.) A possible approach here is to derive another - uniform - set of features. Typically, bag of words features are used for such a situation. For images, this is also known as visual words. Essentially, you first cluster the sub-features to obtain a limited vocabulary. Then you can assign each of the original objects a "text" composed of these "words" and use a distance function such as cosine distance on them.
I see two options here:
Restrict yourself to those features for which all your data-points have a value.
See if you can generate sensible default values for missing features.
However, if possible, you should probably resample all your data-points, so that they all have values for all features.