I am trying to design neural network in Matlab,
I see in many source that the data that used with training neural network
better to be normalize, use [pn,ps] = mapstd(Input) to normalize the input and target,
then I train the network, last thing i test the network by a=sim(net,pn);
my problem is:
how to convert the result to normal result?
last thing, is there any way to train the network with new data to increase the performance?
i mean train with more data where the weighing change slightly to increase the old performance
it is clear that normalize is mean by this function [pn,ps] = mapstd(Input)
all value will be in range of -1 to 1 as i think, the sim of neural network will be normalize result while i have to convert it again to the original range how?
To answer the first question you dont need to go very far. Read the documentation of mapstd(). In there you have a section called "Definition" you have exactly what you are looking for. It is explained why/how to use mapstd() and how to reverse the results in a network (ANN in your case) results after simulation. Read that and you'll now how to do it!
For the second question I will reffer to another SO post, where it is explained better than I what I would do, here it is! Read that carefully because it is very well explained.
Related
I am coding a simple Neural Network, but I have thought of one issue that is bothering me.
This NN is for finding categories in the input. To better understand this, say the categories are "the numbers" (0,1,2...9).
To implement this the output layer is 10 nodes. Say I train this NN with several input -output pairs and save the learned weights somewhere. As the learning process takes quite a lot of time, after that I go and take a break. Come fresh the next day and re-start learning with new input -output pairs. So fair so goo
But what happen if on that time, I decide that I want to recognize hexadecimals (0,1,...9,A,B,,,E,F)... ergo the categories are increasing.
I suspect that would imply changing the structure of the NN and therefore I should retrain the NN from scratch.
Is this so?
Any comment, advice or your share of experience will be greatly appreciated
EDIT: This question has been marked as duplicate. I read the other question and although similar, my question is more concrete. While the other question speaks in generalities and the answer also is quite general- mine is very concrete as I use an example:
If I train a NN to recognize decimal numbers and later on decide to add data to make it recognize hexadecimals, can this be possible? How? Do I have to retrain the whole NN? In other words, does the structure of the NN needs to stay stationary with 10 OR 16 outputs since the beginning?
I would very much appreciate for a concrete answer to this. Thanks
A few considerations
Your training set and testing set should have the same distribution
Unless you have some way of specifying sample weights like some algorithms can you should at all costs avoid training on biased data. This is true for machine learning in general, not only neural networks.
Resuming training from a previous session is equivalent of using good initial values
Technically, you're just using the previous network as initial value instead of a random value. You should keep training in the whole dataset as always, to avoid a biased network.
Short Answer
Yes, you should always retrain your network if by retrain, you mean doing a training routine with the full dataset.
If you just mean retrain as doing a really long training iteration, it isn't your choice anyway. You must always train the network until the training error and testing error (or cross validated error) converge. If you reuse the previously trained network, that will probably happen faster.
You see, this is true no matter what kind of model change. If you change the network architecture, or the dataset, or both (your example), or some other parameter.
Of course, if you change the network architecture, you're going to have a bit of trouble on reusing the previous network. You could reuse the learned parameters from nodes that were kept and randomly initialize the parameters for the new nodes.
Now I use some neural network for OCR and it produces output symbol and some probability for it. Also I have algorithm to split touching characters.
I expected to use probability to decide when to apply splitting.
But now I cannot do this because my network sometimes gives probability for touching characters higher then for normal characters.
Also I cannot understand what happened even after splitting - sometimes normal symbol can be split into two another symbols that both can be recognized with higher probability that initial symbol.
So I need to decide what to do. The question is
can Neural Network at least in theory provide reliable probability for OCR in this sense?
If it is possible then what should I try to do? Should I try to process current output or train network more or choose another network?
Any kind of help or suggestion will be greatly appreciated
Your approach is good and should eventually work given enough training data and given that you remove enough bugs from your preprocessing, splitting, training, etc.
Make sure that you split in the training set (prior to training) exactly the same way that you split the digits when you test them.
But note that Machine Learning produces algorithms that are correct within some accuracy, so you will always find instances that fail. The question is how good is your overall test performance (e.g. % correct digits), and how to increase this to the level that your application requires.
The question is can Neural Network at least in theory provide reliable
probability for OCR in this sense?
Yes
If it is possible then what should I try to do? Should I try to
process current output or train network more or choose another
network?
all of the above until it works! Training size is one of the key factors, and as you grow your training size you can grow your network to improve accuracy.
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 a question regarding the Matlab NN toolbox. As a part of research project I decided to create a Matlab script that uses the NN toolbox for some fitting solutions.
I have a data stream that is being loaded to my system. The Input data consists of 5 input channels and 1 output channel. I train my data on on this configurations for a while and try to fit the the output (for a certain period of time) as new data streams in. I retrain my network constantly to keep it updated.
So far everything works fine, but after a certain period of time the results get bad and do not represent the desired output. I really can't explain why this happens, but i could imagine that there must be some kind of memory issue, since as the data set is still small, everything is ok.
Only when it gets bigger the quality of the simulation drops down. Is there something as a memory which gets full, or is the bad sim just a result of the huge data sets? I'm a beginner with this tool and will really appreciate your feedback. Best Regards and thanks in advance!
Please elaborate on your method of retraining with new data. Do you run further iterations? What do you consider as "time"? Do you mean epochs?
At a first glance, assuming time means epochs, I would say that you're overfitting the data. Neural Networks are supposed to be trained for a limited number of epochs with early stopping. You could try regularization, different gradient descent methods (if you're using a GD method), GD momentum. Also depending on the values of your first few training datasets, you may have trained your data using an incorrect normalization range. You should check these issues out if my assumptions are correct.
This is an on-going venture and some details are purposefully obfuscated.
I have a box that has several inputs and one output. The output voltage changes as the input voltages are changed. The desirability of the output sequence cannot be evaluated until many states pass and a look back process is evaluated.
I want to design a neural network that takes a number of outputs from the box as input and produce the correct input settings for the box to produce the optimal next output.
I cannot train this network using backpropagation. How do I train this network?
Genetic algorithm would be a good candidate here. A chromosome could encode the weights of the neural network. After evaluation you assign a fitness value to the chromosomes based on their performance. Chromosomes with higher fitness value have a higher chance to reproduce, helping to generate better performing chromosomes in the next generation.
Encoding the weights is a relatively simple solution, more complex ones could even define the topology of the network.
You might find some additional helpful information here:
http://en.wikipedia.org/wiki/Neuroevolution
Hillclimbing is the simplest optimization algorithm to implement. Just randomly modify the weights, see if it does better, if not reset them and try again. It's also generally faster than genetic algorithms. However it is prone to getting stuck in local optima, so try running it several times and selecting the best result.