Keras accuracy plots flat while loss plots not flat - machine-learning

I am doing deep learning using a multi-layer perceptron for regression. The loss curve turns flat in the third epoch however accuracy curve remains flat at the beginning. I wonder whether this makes sense.

Since you didn't provide the code, it would be harder to narrow down what is the problem. Being said, here are some pointers that might help you see what is the problem:
Validation set is either small or it is a bad representation of your training set. (bear in mind, if you are using validation_split in fit function, then keras will only take the last percentage of your training set and will keep it the same for all epochs. link]).
You are not using any regularization (Dropout, Regularization, Constraints).
The model could be small (layers- and neurons-wise), so it is underfitting.
Hope these pointers help you with your problem.

Related

Logistic Regression is sensitive to outliers? Using on synthetic 2D dataset

I am currently using sklearn's Logistic Regression function to work on a synthetic 2d problem. The dataset is shown as below:
I'm basic plugging the data into sklearn's model, and this is what I'm getting (the light green; disregard the dark green):
The code for this is only two lines; model = LogisticRegression(); model.fit(tr_data,tr_labels). I've checked the plotting function; that's fine as well. I'm using no regularizer (should that affect it?)
It seems really strange to me that the boundaries behave in this way. Intuitively I feel they should be more diagonal, as the data is (mostly) located top-right and bottom-left, and from testing some things out it seems a few stray datapoints are what's causing the boundaries to behave in this manner.
For example here's another dataset and its boundaries
Would anyone know what might be causing this? From my understanding Logistic Regression shouldn't be this sensitive to outliers.
Your model is overfitting the data (The decision regions it found perform indeed better on the training set than the diagonal line you would expect).
The loss is optimal when all the data is classified correctly with probability 1. The distances to the decision boundary enter in the probability computation. The unregularized algorithm can use large weights to make the decision region very sharp, so in your example it finds an optimal solution, where (some of) the outliers are classified correctly.
By a stronger regularization you prevent that and the distances play a bigger role. Try different values for the inverse regularization strength C, e.g.
model = LogisticRegression(C=0.1)
model.fit(tr_data,tr_labels)
Note: the default value C=1.0 corresponds already to a regularized version of logistic regression.
Let us further qualify why logistic regression overfits here: After all, there's just a few outliers, but hundreds of other data points. To see why it helps to note that
logistic loss is kind of a smoothed version of hinge loss (used in SVM).
SVM does not 'care' about samples on the correct side of the margin at all - as long as they do not cross the margin they inflict zero cost. Since logistic regression is a smoothed version of SVM, the far-away samples do inflict a cost but it is negligible compared to the cost inflicted by samples near the decision boundary.
So, unlike e.g. Linear Discriminant Analysis, samples close to the decision boundary have disproportionately more impact on the solution than far-away samples.

CNN Regression on Grid - Limitation of Convolutional Neural Networks?

I'm working on a (high energy physics related) problem using CNNs.
For understanding the problem, let's consider these examples here.
The left-hand side is the input to the CNN, the right-hand side the desired output. So the network is supposed to cluster the input. The actual algorithm behind this clustering (i.e. how we got the desired output for training) is really complex and we want the CNN to learn this.
I've tried different CNN architectures, for example one similar to the U-net architecture (https://arxiv.org/abs/1505.04597) but also various concatenations of convolutional layers, etc.
The outputs are always really similar (for all architectures).
Here you can see some CNN predictions.
In principle the network is performing quite well, but as you can see, in most cases the CNN output consists of several filled pixels that are directly next to each other, which will never (!) happen in the true cases.
I've been using mean squared error as the loss function in all of the networks.
Do you have any suggestions how one could avoid this problem and improve the networks performance?
Or is this a general limitation to CNNs and in practice it is not possible to solve such a problem using CNNs?
Thank you very much!
My suggestion would be to split up the work. First use a U-Shaped NN to find the activations in a binary segmentation task (like in your paper) and then regress on the found activations to find their final values. In my experience this works way better than doing regression on large images, because the MSE will result in blurry outputs, as you have observed.
The CNN does not know that you wanted a sharp result. As mentioned by #Thomas, MSE tends to give you blurry result as it is the nature of that loss function. Giving a blurry result does not introduce large loss in MSE.
An easy modification would be to use L1 Loss (absolute difference instead of squared error). It has a constant gradient unlike MSE whose gradient decreases with error.
If you really wanted a sharp result, it would be easier to add a manual step -- non maximum suppression (NMS). In practice, a 3x3 box-max filter might do.

Training Multi-GPU on Tensorflow: a simpler way?

I have been using the training method proposed in the cifar10_multi_gpu_train example for (local) multi-gpu training, i.e., creating several towers and then average the gradient. However, I was wondering the following: What does happen if I just take the losses coming from the different GPUs, sum them up and then just apply gradient descent to that new loss.
Would that work? Probably this is a silly question, and there must be a limitation somewhere. So I would be happy if you could comment on this.
Thanks and best regards,
G.
It would not work with the sum. You would get a bigger loss and consequentially bigger and probably erroneous gradients. While averaging the gradients you get an average of the direction that the weights have to take in order to minimize the loss, but each single direction is the one computed for the exact loss value.
One thing that you can try is to run the towers independently and then average the weights from time to time, slower convergence rate but faster processing on each node.

Pre-processing data: Normalizing data labels in regression?

Recently I was told that the labels of regression data should also be normalized for better result but I am pretty doubtful of that. I have never tried normalizing labels in both regression and classification that's why I don't know if that state is true or not. Can you please give me a clear explanation (mathematically or in experience) about this problem?
Thank you so much.
Any help would be appreciated.
When you say "normalize" labels, it is not clear what you mean (i.e. whether you mean this in a statistical sense or something else). Can you please provide an example?
On Making labels uniform in data analysis
If you are trying to neaten labels for use with the text() function, you could try the abbreviate() function to shorten them, or the format() function to align them better.
The pretty() function works well for rounding labels on plot axes. For instance, the base function hist() for drawing histograms calls on Sturges or other algorithms and then uses pretty() to choose nice bin sizes.
The scale() function will standardize values by subtracting their mean and dividing by the standard deviation, which in some circles is referred to as normalization.
On the reasons for scaling in regression (in response to comment by questor). Suppose you regress Y on covariates X1, X2, ... The reasons for scaling covariates Xk depend on the context. It can enable comparison of the coefficients (effect sizes) of each covariate. It can help ensure numerical accuracy (these days not usually an issue unless covariates on hugely different scales and/or data is big). For a readable intro see Psychosomatic medicine editors' guide. For a mathematically intense discussion see Sylvain Sardy's guide.
In particular, in Bayesian regression, rescaling is advisable to ensure convergence of MCMC estimation; e.g. see this discussion.
You mean features not labels.
It is not necessary to normalize your features for regression or classification, even though in some cases, it is a trick that can help converging faster. You might want to check this post.
To my experience, when using a simple model like a linear regression with only a few variables, keeping the features as they are (without normalization) is preferable since the model is more interpretable.
It may be that what you mean is that you should scale your labels. The reason is so convergence is faster, and you don't get numeric instability.
For example, if your labels are in the range (1000, 1000000) and the weights are initialized close to zero, a mse loss would be so large, you'd likely get NaN errors.
See https://datascience.stackexchange.com/q/22776/38707 for a similar discussion.
for a regression problem with algorithms including decision tree or logistic regression and linear regression I tested in two modes: 1- with label scaling using MinMaxScaler 2- without label scaling the result that i got was : r2 score is the same in 2 mode mse and mae scales
for diabetes dataset using linear regression the result before and after is
without scaling:
Mean Squared Error: 3424.3166
Mean Absolute Error: 46.1742
R2_score : 0.33
after scaling labels:
Mean Squared Error: 0.0332
Mean Absolute Error: 0.1438
R2_score : 0.33
also below link can be useful which says scaling can be helpful in fast convergence enter scale or not scale labels in deep leaning?

How to interpret the results of a training/validation learning curve?

I am using the Random Forest classifier in the Scikit package and have plotted F1 scores versus training set size. The red is the training set F1 scores and the green is the scores for the validation set. This is about what I expected but I would like some advice on interpretation.
I see that there is some significant variance, yet the validation curve appears to be converging. Should I assume that adding data would do little to affect the variance given the convergence or am I jumping to conclusion about the rate of convergence?
Is the amount of variance here significant enough to warrant taking further actions that may increase the bias slightly? I realize this is a fairly domain-specific question but I wonder if there is any general guidelines for how much variance is worth a bit of bias tradeoff?
I see that there is some significant variance, yet the validation curve appears to be converging. Should I assume that adding data would do little to affect the variance given the convergence or am I jumping to conclusion about the rate of convergence?
This seems true conditioning on your learning procedure, thus in particular - selection of hyperparameters. Thus it does not mean that given different set of hyperparameters the same effect would occur. It only seems that given current setting - rate of convergence is relatively small thus getting to 95% would probably require significant amounts of data.
Is the amount of variance here significant enough to warrant taking further actions that may increase the bias slightly? I realize this is a fairly domain-specific question but I wonder if there is any general guidelines for how much variance is worth a bit of bias tradeoff?
Yes, in general - these kind of curves at least do not reject option to go for higher bias. You clearly overfit towards training set. On the other hand, trees usually do that, thus increasing bias might be hard without changing the model. One option that I would suggest is going for Extremely Randomized Trees, which is nearly the same as Random Forest, but with randomly chosen threshold instead of full optimization. They have significantly bigger bias and should take these curves a bit closer to each other.
Obviously there is no guarantee - as you said, this is data specific, but the general characteristic looks promising (however might require changing the model).

Resources