I have done a lot of research in terms of neural networks - especially convolutional neural networks. My Network produces a linear output using the identity function. After several trainings, the MSE was bounded to a minimum.
After having a closer look into the results, I found out, that the MSE per subject differs per training. I.e. Net 1 is doing good work on person 1 and 2, but not so good on person 3 and 4. Net 2 which is trained using the exact same training dataset gets the same MSE, but is doing better on person 3/4 and worse on 1/2.
After this I came up with the idea of a unsupervised post training. There might be a correlation between person 1/2 and 3/4. Maybe a smaller head or what so ever. So I might switch the weights depending on what the learner tells me to use? Has anyone doen that before? Is there any literature?
Related
Consider the training process of deep FF neural network using mini-batch gradient descent. As far as I understand, at each epoch of the training we have different random set of mini-batches. Then iterating over all mini batches and computing the gradients of the NN parameters we will get random gradients at each iteration and, therefore, random directions for the model parameters to minimize the cost function. Let's imagine we fixed the hyperparameters of the training algorithm and started the training process again and again, then we would end up with models, which completely differs from each other, because in those trainings the changes of model parameters were different.
1) Is it always the case when we use such random based training algorithms?
2) If it is so, where is the guaranty that training the NN one more time with the best hyperparameters found during the previous trainings and validations will yield us the best model again?
3) Is it possible to find such hyperparameters, which will always yield the best models?
Neural Network are solving a optimization problem, As long as it is computing a gradient in right direction but can be random, it doesn't hurt its objective to generalize over data. It can stuck in some local optima. But there are many good methods like Adam, RMSProp, momentum based etc, by which it can accomplish its objective.
Another reason, when you say mini-batch, there is at least some sample by which it can generalize over those sample, there can be fluctuation in the error rate, and but at least it can give us a local solution.
Even, at each random sampling, these mini-batch have different-2 sample, which helps in generalize well over the complete distribution.
For hyperparameter selection, you need to do tuning and validate result on unseen data, there is no straight forward method to choose these.
Training a neural network where N training examples contains same attributes and classification. E.g :
Training example1 = [1,1,1,1] , classification = [1]
Training example2 = [1,1,1,1] , classification = [1]
It's wasting training time training with 'Training example2' as it will not contribute to the overall quality of the neural network ?
I think that if it doesn't harm your learning process a lot - would left them in your training set. The reason behind this is stated in the following points :
Usually - the process of learning of a neural network has it probability theory interpretation. You are learning some conditional distribiution P(y|x). In this case it's obvious that the more learning examples you have, the more accurate approximation you will have.
Very often your data hasn't a functional form where y = f(x). In this case you need to deal with uncertainty. In this case the more examples you have - the more sure you are about your predictions.
In some comments someone said that if e.g. every example occurs twice in dataset then this might be redundant. But checking if your data comes from such distribiution is either obvious or too computationally costly to check. So you shouldn't care about this.
One example where the best practice is to use common training examples less frequently is in word2vec. See this link for more information.
https://www.quora.com/How-does-sub-sampling-of-frequent-words-work-in-the-context-of-Word2Vec
Recently, I am trying to using Matlab build-in neural networks toolbox to accomplish my classification problem. However, I have some questions about the parameter settings.
a. The number of neurons in the hidden layer:
The example on this page Matlab neural networks classification example shows a two-layer (i.e. one-hidden-layer and one-output-layer) feed forward neural networks. In this example, it uses 10 neurons in the hidden layer
net = patternnet(10);
My first question is how to define the best number of neurons for my classification problem? Should I use cross-validation method to get the best performed number of neurons using a training data set?
b. Is there a method to choose three-layer or more multi-layer neural networks?
c. There are many different training method we can use in the neural networks toolbox. A list can be found at Training methods list. The page mentioned that the fastest training function is generally 'trainlm'; however, generally speaking, which one will perform best? Or it totally depends on the data set I am using?
d. In each training method, there is a parameter called 'epochs', which is the training iteration for my understanding. For each training method, Matlab defined the maximum number of epochs to train. However, from the example, it seems like 'epochs' is another parameter we can tune. Am I right? Or we just set the maximum number of epochs or leave it as default?
Any experience with Matlab neural networks toolbox is welcome and thanks very much for your reply. A.
a. You can refer to How to choose number of hidden layers and nodes in neural network? and ftp://ftp.sas.com/pub/neural/FAQ3.html#A_hu
Surely you can do cross-validation to determine the parameter of best number of neurons. But it's not recommended as it's more suitable to use it in the stage of weights training of a certain network.
b. Refer to ftp://ftp.sas.com/pub/neural/FAQ3.html#A_hl
And for more layers of neural network, you can refer to Deep Learning, which is very hot in recent years and gets state-of-the-art performances in many of the pattern recognition tasks.
c. It depends on your data. trainlm performs better on function fitting (nonlinear regression) problems than on pattern recognition problems while training large networks and pattern recognition networks, trainscg and trainrp are good choices. Generally, Gradient Descent and Resilient Backpropagation is recommended. More detailed comparison can be found here: http://www.mathworks.cn/cn/help/nnet/ug/choose-a-multilayer-neural-network-training-function.html
d. Yes, you're right. We can tune the epochs parameter. Generally you can output the recognition results/accuracy at every epoch and you will see that it is promoting more and more slowly, and the more epochs the more computing time. You can make a compromise between the accuracy and computation time.
For part b of your question:
You can use like this code:
net = patternnet([10 15 20]);
This script create a network with 3 hidden layer that first layer has 10 neurons, second layer has 15 neurons and 3th layer has 20 neurons.
I would like to ask for ideas what options there is for training a MATLAB ANN (artificial neural network) continuously, i.e. not having a pre-prepared training set? The idea is to have an "online" data stream thus, when first creating the network it's completely untrained but as samples flow in the ANN is trained and converges.
The ANN will be used to classify a set of values and the implementation would visualize how the training of the ANN gets improved as samples flows through the system. I.e. each sample is used for training and then also evaluated by the ANN and the response is visualized.
The effect that I expect is that for the very first samples the response of the ANN will be more or less random but as the training progress the accuracy improves.
Any ideas are most welcome.
Regards, Ola
In MATLAB you can use the adapt function instead of train. You can do this incrementally (change weights every time you get a new piece of information) or you can do it every N-samples, batch-style.
This document gives an in-depth run-down on the different styles of training from the perspective of a time-series problem.
I'd really think about what you're trying to do here, because adaptive learning strategies can be difficult. I found that they like to flail all over compared to their batch counterparts. This was especially true in my case where I work with very noisy signals.
Are you sure that you need adaptive learning? You can't periodically re-train your NN? Or build one that generalizes well enough?
I'm trying to build an app to detect images which are advertisements from the webpages. Once I detect those I`ll not be allowing those to be displayed on the client side.
Basically I'm using Back-propagation algorithm to train the neural network using the dataset given here: http://archive.ics.uci.edu/ml/datasets/Internet+Advertisements.
But in that dataset no. of attributes are very high. In fact one of the mentors of the project told me that If you train the Neural Network with that many attributes, it'll take lots of time to get trained. So is there a way to optimize the input dataset? Or I just have to use that many attributes?
1558 is actually a modest number of features/attributes. The # of instances(3279) is also small. The problem is not on the dataset side, but on the training algorithm side.
ANN is slow in training, I'd suggest you to use a logistic regression or svm. Both of them are very fast to train. Especially, svm has a lot of fast algorithms.
In this dataset, you are actually analyzing text, but not image. I think a linear family classifier, i.e. logistic regression or svm, is better for your job.
If you are using for production and you cannot use open source code. Logistic regression is very easy to implement compared to a good ANN and SVM.
If you decide to use logistic regression or SVM, I can future recommend some articles or source code for you to refer.
If you're actually using a backpropagation network with 1558 input nodes and only 3279 samples, then the training time is the least of your problems: Even if you have a very small network with only one hidden layer containing 10 neurons, you have 1558*10 weights between the input layer and the hidden layer. How can you expect to get a good estimate for 15580 degrees of freedom from only 3279 samples? (And that simple calculation doesn't even take the "curse of dimensionality" into account)
You have to analyze your data to find out how to optimize it. Try to understand your input data: Which (tuples of) features are (jointly) statistically significant? (use standard statistical methods for this) Are some features redundant? (Principal component analysis is a good stating point for this.) Don't expect the artificial neural network to do that work for you.
Also: remeber Duda&Hart's famous "no-free-lunch-theorem": No classification algorithm works for every problem. And for any classification algorithm X, there is a problem where flipping a coin leads to better results than X. If you take this into account, deciding what algorithm to use before analyzing your data might not be a smart idea. You might well have picked the algorithm that actually performs worse than blind guessing on your specific problem! (By the way: Duda&Hart&Storks's book about pattern classification is a great starting point to learn about this, if you haven't read it yet.)
aplly a seperate ANN for each category of features
for example
457 inputs 1 output for url terms ( ANN1 )
495 inputs 1 output for origurl ( ANN2 )
...
then train all of them
use another main ANN to join results