Unstable output values from ANN and improving accuracy - statistics

I am trying to develop an Artificial Neural Network using PyBrain to model biological data. My ANN compiles and runs, but its accuracy value is very low, never surpassing ~62%. From a coding perspective, how can I improve the ANN's accuracy? Something I noticed was that each time, the outputs of the ANN are not the same, either, even though the test data set doesn't change--is there a reason the ANN is acting to unstably, and how can I improve this?
Thank you! :)

If you creating new network each time you run your script then it is normal that outputs are different.
Each time you create ANN pybrain initialize weights of connections with random values (range 0 to 1).
You can save your ANN with NetworkWriter and read it with NetworkReader in pybrain.tools.customxml (see code documentation for reference, pybrain API is missing few things).
You can adjust training process with learning rate and momentum. Also you could apply more training epoch to your network.
If you provide your code I could say more.

Related

Abrupt increase in RMSE in LSTM while working on Time Series Prediction

I have the following LSTM network(Fig 1) for predicting the Bitcoin Price. The input is every hour close price of Bitcoin. I am facing some issues and any advice is appreciated.
Earlier on the same network, my RMSE on testing and training set was 6.71 and 7.41 RMSE. I recompiled the whole code and there was an abrupt increase to 233.51 for the training set and 345.56 for the testing set. Can anyone help me with finding out the reason behind this?
Also, How to improve the accuracy of my network as it very low in every iteration?
How should I decide the parameters for my LSTM network. (units, epochs, batch_size, time_steps to input)
Thank you in advance for any help extended.
Your question requires a lot more information. For example, data size, timesteps lookback, data preprocessing procedure, etc. But I would recommend you to debug your problem with the following method. First, check whether your input/output data are processed properly or not. Then, try to train the simpler model apart from LSTM as it could result in overfitting. But sometimes, if the input signal is too random, it is normal that your model results would highly fluctuate as there's no correlation in data.
PS. never use the Machine Learning model to predict stock price. It never works.

Best Way to Overcome Early Convergence for Machine Learning Model

I have a machine learning model built that tries to predict weather data, and in this case I am doing a prediction on whether or not it will rain tomorrow (a binary prediction of Yes/No).
In the dataset there is about 50 input variables, and I have 65,000 entries in the dataset.
I am currently running a RNN with a single hidden layer, with 35 nodes in the hidden layer. I am using PyTorch's NLLLoss as my loss function, and Adaboost for the optimization function. I've tried many different learning rates, and 0.01 seems to be working fairly well.
After running for 150 epochs, I notice that I start to converge around .80 accuracy for my test data. However, I would wish for this to be even higher. However, it seems like the model is stuck oscillating around some sort of saddle or local minimum. (A graph of this is below)
What are the most effective ways to get out of this "valley" that the model seems to be stuck in?
Not sure why exactly you are using only one hidden layer and what is the shape of your history data but here are the things you can try:
Try more than one hidden layer
Experiment with LSTM and GRU layer and combination of these layers together with RNN.
Shape of your data i.e. the history you look at to predict the weather.
Make sure your features are scaled properly since you have about 50 input variables.
Your question is little ambiguous as you mentioned RNN with a single hidden layer. Also without knowing the entire neural network architecture, it is tough to say how can you bring in improvements. So, I would like to add a few points.
You mentioned that you are using "Adaboost" as the optimization function but PyTorch doesn't have any such optimizer. Did you try using SGD or Adam optimizers which are very useful?
Do you have any regularization term in the loss function? Are you familiar with dropout? Did you check the training performance? Does your model overfit?
Do you have a baseline model/algorithm so that you can compare whether 80% accuracy is good or not?
150 epochs just for a binary classification task looks too much. Why don't you start from an off-the-shelf classifier model? You can find several examples of regression, classification in this tutorial.

Why does removing validation samples from Keras model improve test accuracy so much

I'm doing a programming assignment for Andrew Ng's Deep Learning course on Convolutional Models that involves training and evaluating a model using Keras. What I've observed after a little playing with various knobs is something curious: The test accuracy of the model greatly improves (from 50 percentile to 90 percentile) by setting the validation_fraction parameter on the Model.fit operation to 0. This is surprising to me; I would have thought that eliminating the validation samples would lead to over-fitting of the model, which would, in turn, reduce accuracy on the test set.
Can someone please explain why this is happening?
You're right, there is more training data, but the increase is pretty negligible since dI was setting the validation fraction to 0.1, so that would increase the training data by 11.111...% However, thinking about it some more, I realized that removing the validation step doesn't have any effect on the model, hence no impact on test accuracy. I think that I must have changed some other parameter, too, though I don't remember which.
As Matias says, it means there is more training data to work with.
However, I'd also make sure that the test accuracy is actually increasing from 50 to 90% consistently. Run it over a couple times to make sure. There is a possibility that, because there is very little validation samples, that the model got lucky. That's why it is important to have a lot of validation data - to make sure the model isn't just getting lucky, and that there's actually a method to the madness.
I go over some of the "norms" when it comes to training and testing data in my book about stock prediction (another great way in my opinion to learn about Deep Learning). Feel free to check it out and learn more, as it's great for beginners.
Good Luck!

Where do the input filters come from in conv-neural nets (MNIST Example)

I am a newby to the convolutional neural nets... so this may be an ignorant question.
I have followed many examples and tutorials now on the MNIST example in TensforFlow. In the CNN examples, all authors talk bout using the 'input filters' to run in the CNN. But no one that I can find mentions WHERE they come from. Can anyone answer where these come from? Or are they magically obtained from the input images.
Thanks! Chris
This is an image that one professor uses, be he does not exaplain if he made them or TensorFlow auto-extracts these somehow.
Disclaimer: I am not an expert, more of an enthusiast.
To cut a long story short: filters are the CNN equivalent of weights, and all a neural network essentially does is learning their optimal values.
Which it does by iterating through a training dataset, making predictions, comparing them to the label/value already assigned to each training unit (usually an image in case of a CNN) and adjusting weights to minimize the error function (the difference between the predicted value and the actual value).
Initial values of filters/weights do not matter that much, so although they might affect the speed of convergence to a small degree, I believe they are often assigned random values.
It is the job of the neural network to figure out the optimal weights, not of the person implementing it.

Multi layer perceptron for OCR [closed]

Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
I intend to use a multi layer perceptron network trained with backpropagation (one hidden layer, inputs served as 8x8 bit matrices containing the B/W pixels from the image). The following questions arise:
which type of learning should I use: batch or on-line?
how could I estimate the right number of nodes in the hidden layer? I intend to process the 26 letter of english alphabet.
how could I stop the training process, to avoid overfitting?
(not quite related) is there another better NN prved to perform better than MLP? I know about MLP stucking in local minima, overfitting and so on, so is there a better (soft computing-based) approach?
Thanks
Most of these questions are things that you need to try different options to see what works best. That is the problem with ANNs. There is no "best" way to do almost anything. You need to find out what works for your specific problem. Nevertheless, I will give my advice for your questions.
1) I prefer incremental learning. I think it is important for the network weights to be updated after each pattern.
2) This is a tough question. It really depends on the complexity of your network. How many input nodes, output nodes, and training patterns that there are. For your problem, I might start with 100 and try ranges up and down from 100 to see if there is improvement.
3) I usually calculate the total error of the network when applied to the test set (not the training set) after each epoch. If that error increases for about 5 epochs, I will stop training and then use the network that was created before the increase occurred. It is important not to use the error of the training set when deciding to stop training. This is what will cause overfitting.
4) You could also try a probabilistic neural network if you are representing your output as 26 nodes, each representing a letter of the alphabet. This network architecture is good for classification problems. Again, it may be a good idea just to try a few different architectures to see what works best for your problem.
Regarding number 3, one way to find out when your ANN starts to overfit is by graphing the accuracy of the net on your training data and your test data vs the number of epochs performed. At some point, as your training accuracy continues to increase (tending towards 100%), your test accuracy will probably start to actually decrease because the ANN is overfitting to the training data. See what epoch that starts to happen and make sure not to train past that.
If your data is very regular and consistent, then it might not overfit until very late in the game, or not at all. And if your data is highly irregular, then your ANN will start to overfit much earlier.
Also, a way to test how regular your data is is to do something like k-fold cross validation.

Resources