I have been experimenting with neural networks these days. I have come across a general question regarding the activation function to use. This might be a well known fact to but I couldn't understand properly. A lot of the examples and papers I have seen are working on classification problems and they either use sigmoid (in binary case) or softmax (in multi-class case) as the activation function in the out put layer and it makes sense. But I haven't seen any activation function used in the output layer of a regression model.
So my question is that is it by choice we don't use any activation function in the output layer of a regression model as we don't want the activation function to limit or put restrictions on the value. The output value can be any number and as big as thousands so the activation function like sigmoid to tanh won't make sense. Or is there any other reason? Or we actually can use some activation function which are made for these kind of problems?
for linear regression type of problem, you can simply create the Output layer without any activation function as we are interested in numerical values without any transformation.
more info :
https://machinelearningmastery.com/regression-tutorial-keras-deep-learning-library-python/
for classification :
You can use sigmoid, tanh, Softmax etc.
If you have, say, a Sigmoid as an activation function in output layer of your NN you will never get any value less than 0 and greater than 1.
Basically if the data your're trying to predict are distributed within that range you might approach with a Sigmoid function and test if your prediction performs well on your training set.
Even more general, when predict a data you should come up with the function that represents your data in the most effective way.
Hence if your real data does not fit Sigmoid function well you have to think of any other function (e.g. some polynomial function, or periodic function or any other or a combination of them) but you also should always care of how easily you will build your cost function and evaluate derivatives.
Just use a linear activation function without limiting the output value range unless you have some reasonable assumption about it.
Related
I am currently learning a little bit about neural networks. One question I can't really get behind is about how neural networks reflect non-linear behavior. From my understanding there is no possibility to reflect non-linear behavior inside a compact set using a neural network.
For example if I would take the function from this question:
y = x^2
and I would use a neural network with a single input and single output the best the neural network could do for each compact set [x0...xn] is a linear function spanning from one end of the set to the other, as at the end all calculations inside the net are linear.
Do I have some misunderstanding about this concept?
The ANN's capabilties to model non-linear behaviour arise from the (usually) non-linear activation function.
If the activation function is linear, then the process of training the network is just another way to create a linear (or multi-linear) fit of input and output data.
Activation function in neural networks is exactly the part, that brings non-linearity. If you use linear activation function, then you cannot train non-linear model (thus fit quadratic or other non-linear functions).
The part, I guess, you are interested in is Universal Approximation Theorem, which says that any continuous function can be approximated with a neural network with a single hidden layer (some assumptions on activation function are applied thou). Take into account, that this theorem does not say anything on optimization of such a network (it does not guarantee you can train such a network with a specific algorithm, but only that such a network exists). Also it does not say anything on the number of neurons you should use.
You can check following links, to get more details:
Original proof with sigmoid activation function: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.441.7873&rep=rep1&type=pdf
And a more friendly derivation: http://mcneela.github.io/machine_learning/2017/03/21/Universal-Approximation-Theorem.html
I'm currently trying to use an autoencoder network for dimensionality reduction.
(i.e. using the bottleneck activation as the compressed feature)
I noticed that a lot of studies that used autoencoder for this task uses a linear bottleneck layer.
By intuition, I think this makes sense since the usage of non-linear activation function may reduce the bottleneck feature's capability to represent the principle information contained within the original feature.
(e.g., ReLU ignores the negative values and sigmoid suppresses values too high or too low)
However, is this correct? And is using linear bottleneck layer for autoencoder necessary?
If it's possible to use a non-linear bootleneck layer, what activation function would be the best choice?
Thanks.
No, you are not limited to linear activation functions. An example of that is this work, where they use the hidden state of the GRU layers as an embedding for the input. The hidden state is obtained by using non-linear tanh and sigmoid functions in its computation.
Also, there is nothing wrong with 'ignoring' the negative values. The sparsity may, in fact, be beneficial. It can enhance the representation. The noise that can be created by other functions such as identity or sigmoid function may introduce false dependencies where there are none. By using ReLU we can represent the lack of dependency properly (as a zero) as opposed to some near zero value which is likely for e.g. sigmoid function.
I am learning to build neural networks for regression problems. It works well approximating linear functions. Setup with 1-5–1 units with linear activation functions in hidden and output layers does the trick and results are fast and reliable. However, when I try to feed it simple quadratic data (f(x) = x*x) here is what happens:
With linear activation function, it tries to fit a linear function through dataset
And with TANH function it tries to fit a a TANH curve through the dataset.
This makes me believe that the current setup is inherently unable to learn anything but a linear relation, since it's repeating the shape of activation function on the chart. But this may not be true because I've seen other implementations learn curves just perfectly. So I may be doing something wrong. Please provide your guidance.
About my code
My weights are randomized (-1, 1) inputs are not normalized. Dataset is fed in random order. Changing learning rate or adding layers, does not change the picture much.
I've created a jsfiddle,
the place to play with is this function:
function trainingSample(n) {
return [[n], [n]];
}
It produces a single training sample: an array of an input vector array and a target vector array.
In this example it produces an f(x)=x function. Modify it to be [[n], [n*n]] and you've got a quadratic function.
The play button is at the upper right, and there also are two input boxes to manually input these values. If target (right) box is left empty, you can test the output of the network by feedforward only.
There is also a configuration file for the network in the code, where you can set learning rate and other things. (Search for var Config)
It's occurred to me that in the setup I am describing, it is impossible to learn non–linear functions, because of the choice of features. Nowhere in forward pass we have input dependency of power higher than 1, that's why I am seeing a snapshot of my activation function in the output. Duh.
What's the correct way to do 'disjoint' classification (where the outputs are mutually exclusive, i.e. true probabilities sum to 1) in FANN since it doesn't seems to have an option for softmax output?
My understanding is that using sigmoid outputs, as if doing 'labeling', that I wouldn't be getting the correct results for a classification problem.
FANN only supports tanh and linear error functions. This means, as you say, that the probabilities output by the neural network will not sum to 1. There is no easy solution to implementing a softmax output, as this will mean changing the cost function and hence the error function used in the backpropagation routine. As FANN is open source you could have a look at implementing this yourself. A question on Cross Validated seems to give the equations you would have to implement.
Although not the mathematically elegant solution you are looking for, I would try play around with some cruder approaches before tackling the implementation of a softmax cost function - as one of these might be sufficient for your purposes. For example, you could use a tanh error function and then just renormalise all the outputs to sum to 1. Or, if you are actually only interested in what the most likely classification is you could just take the output with the highest score.
Steffen Nissen, the guy behind FANN, presents an example here where he tries to classify what language a text is written in based on letter frequency. I think he uses a tanh error function (default) and just takes the class with the biggest score, but he indicates that it works well.
I just started playing around with neural networks and, as I would expect, in order to train a neural network effectively there must be some relation between the function to approximate and activation function.
For instance, I had good results using sin(x) as an activation function when approximating cos(x), or two tanh(x) to approximate a gaussian. Now, to approximate a function about which I know nothing I am planning to use a cocktail of activation functions, for instance a hidden layer with some sin, some tanh and a logistic function. In your opinion does this make sens?
Thank you,
Tunnuz
While it is true that different activation functions have different merits (mainly for either biological plausibility or a unique network design like radial basis function networks), in general you be able to use any continuous squashing function and expect to be able to approximate most functions encountered in real world training data.
The two most popular choices are the hyperbolic tangent and the logistic function, since they both have easily calculable derivatives and interesting behavior around the axis.
If neither if those allows you to accurately approximate your function, my first response wouldn't be to change activation functions. Rather, you should first investigate your training set and network training parameters (learning rates, number of units in each pool, weight decay, momentum, etc.).
If your still stuck, step back and make sure your using the right architecture (feed forward vs. simple recurrent vs. full recurrent) and learning algorithm (back-propagation vs. back-prop through time vs. contrastive hebbian vs. evolutionary/global methods).
One side note: Make sure you never use a linear activation function (except for output layers or crazy simple tasks), as these have very well documented limitations, namely the need for linear separability.