I'm starting neural networks, currently following mostly D. Kriesel's tutorial. Right off the beginning it introduces at least three (different?) learning rules (Hebbian, delta rule, backpropagation) concerning supervised learning.
I might be missing something, but if the goal is merely to minimize the error, why not just apply gradient descent over Error(entire_set_of_weights)?
Edit: I must admit the answers still confuse me. It would be helpful if one could point out the actual difference between those methods, and the difference between them and straight gradient descent.
To stress it, these learning rules seem to take the layered structure of the network into account. On the other hand, finding the minimum of Error(W) for the entire set of weights completely ignores it. How does that fit in?
One question is how to apportion the "blame" for an error. The classic Delta Rule or LMS rule is essentially gradient descent. When you apply Delta Rule to a multilayer network, you get backprop. Other rules have been created for various reasons, including the desire for faster convergence, non-supervised learning, temporal questions, models that are believed to be closer to biology, etc.
On your specific question of "why not just gradient descent?" Gradient descent may work for some problems, but many problems have local minima, which naive gradient descent will get stuck in. The initial response to that is to add a "momentum" term, so that you might "roll out" of a local minimum; that's pretty much the classic backprop algorithm.
First off, note that "backpropagation" simply means that you apply the delta rule on each layer from output back to input so it's not a separate rule.
As for why not a simple gradient descent, well, the delta rule is basically gradient descent. However, it tends to overfit the training data and doesn't generalize as efficiently as techniques which don't try to decay the error margin to zero. This makes sense because "error" here simply means the difference between our samples and the output - they are not guaranteed to accurately represent all possible inputs.
Backpropagation and naive gradient descent also differ in computational efficiency. Backprop is basically taking the networks structure into account and for each weight only calculates the actually needed parts.
The derivative of the error with respects to the weights is splitted via the chainrule into: ∂E/∂W = ∂E/∂A * ∂A/∂W. A is the activations of particular units. In most cases, the derivatives will be zero because W is sparse due to the networks topology. With backprop, you get the learning rules on how to ignore those parts of the gradient.
So, from a mathematical perspective, backprop is not that exciting.
there may be problems which for example make backprop run into local minima. Furthermore, just as an example, you can't adjust the topology with backprop. There are also cool learning methods using nature-inspired metaheuristics (for instance, evolutionary strategies) that enable adjusting weight AND topology (even recurrent ones) simultaneously. Probably, I will add one or more chapters to cover them, too.
There is also a discussion function right on the download page of the manuscript - if you find other hazzles that you don't like about the manuscript, feel free to add them to the page so I can change things in the next edition.
Greetz,
David (Kriesel ;-) )
Related
I'm recently studying the theory about neural network. And I'm a little confuse about the role of gradient descent and activation function in ANN.
From what I understand, the activation function is used for transforming the model to non-linear model. So that it can solve the problem that is not linear separable. And the gradient descent is the tool to help model learn.
So my questions are :
If I use an activation function such as sigmoid for the model, but instead of using gradient decent to improve the model, I use classic perceptron learning rule : Wj = Wj + a*(y-h(x)), where the h(x) is the sigmoid function with the net input. Can the model learn the non-linear separable problem ?
If I do not include the non-linear activation function in the model. Just simple net input : h(x) = w0 + w1*x1 + ... + wj*xj. And using gradient decent to improve the model. Can the model learn the non-linear separable problem ?
I'm really confused about this problem, that which one is the main reason that the model can learn non-linear separable problem.
Supervised Learning 101
This is a pretty deep question, so I'm going to review the basics first to make sure we understand each other. In its simplest form, supervised learning, and classification in particular, attempts to learn a function f such that y=f(x), from a set of observations {(x_i,y_i)}. The following problems arise in practice:
You know nothing about f. It could be a polynomial, exponential, or some exotic highly non-linear thing that doesn't even have a proper name in math.
The dataset you're using to learn is just a limited, and potentially noisy, subset of the true data distribution you're trying to learn.
Because of this, any solution you find will have to be approximate. The type of architecture you will use will determine a family of function h_w(x), and each value of w will represent one function in this family. Note that because there is usually an infinite number of possible w, the family of functions h_w(x) are often infinitely large.
The goal of learning will then be to determine which w is most appropriate. This is where gradient descent intervenes: it is just an optimisation tool that helps you pick reasonably good w, and thus select a particular model h(x).
The problem is, the actual f function you are trying to approximate may not be part of the family h_w you decided to pick, and so you are .
Answering the actual questions
Now that the basics are covered, let's answer your questions:
Putting a non-linear activation function like sigmoid at the output of a single layer model ANN will not help it learn a non-linear function. Indeed a single layer ANN is equivalent to linear regression, and adding the sigmoid transforms it into Logistic Regression. Why doesn't it work? Let me try an intuitive explanation: the sigmoid at the output of the single layer is there to squash it to [0,1], so that it can be interpreted as a class membership probability. In short, the sigmoid acts a differentiable approximation to a hard step function. Our learning procedure relies on this smoothness (a well-behaved gradient is available everywhere), and using a step function would break eg. gradient descent. This doesn't change the fact that the decision boundary of the model is linear, because the final class decision is taken from the value of sum(w_i*x_i). This is probably not really convincing, so let's illustrate instead using the Tensorflow Playground. Note that the learning rule does not matter here, because the family of function you're optimising over consist only of linear functions on their input, so you will never learn a non-linear one!
If you drop the sigmoid activation, you're left with a simple linear regression. You don't even project your result back to [0,1], so the output will not be simple to interpret as class probability, but the final result will be the same. See the Playground for a visual proof.
What is needed then?
To learn a non-linearly separable problem, you have several solutions:
Preprocess the input x into x', so that taking x' as an input makes the problem linearly separable. This is only possible if you know the shape that the decision boundary should take, so generally only applicable to very simple problems. In the playground problem, since we're working with a circle, we can add the squares of x1 and x2 to the input. Although our model is linear in its input, an appropriate non-linear transformation of the input has been carefully selected, so we get an excellent fit.
We could try to automatically learn the right representation of the data, by adding one or more hidden layers, which will work to extract a good non-linear transformation. It can be proven that using a single hidden layer is enough to approximate anything as long as make the number of hidden neurons high enough. For our example, we get a good fit using only a few hidden neurons with ReLU activations. Intuitively, the more neurons you add, the more "flexible" the decision boundary can become. People in deep learning have been adding depth rather than width because it can be shown that making the network deeper makes it require less neurons overall, even though it makes training more complex.
Yes, gradient descent is quite capable of solving a non-linear problem. The method works as long as the various transformations are roughly linear within a "delta" of the adjustments. This is why we adjust our learning rates: to stay within the ranges in which linear assumptions are relatively accurate.
Non-linear transformations give us a better separation to implement the ideas "this is boring" and "this is exactly what I'm looking for!" If these functions are smooth, or have a very small quantity of jumps, we can apply our accustomed approximations and iterations to solve the overall system.
Determining the useful operating ranges is not a closed-form computation, by any means; as with much of AI research, it requires experimentation and refinement. The direct answer to your question is that you've asked the wrong entity -- try the choices you've listed, and see which works best for your application.
Many of the papers I have read so far have this mentioned "pre-training network could improve computational efficiency in terms of back-propagating errors", and could be achieved using RBMs or Autoencoders.
If I have understood correctly, AutoEncoders work by learning the
identity function, and if it has hidden units less than the size of
input data, then it also does compression, BUT what does this even have
anything to do with improving computational efficiency in propagating
error signal backwards? Is it because the weights of the pre
trained hidden units does not diverge much from its initial values?
Assuming data scientists who are reading this would by theirselves
know already that AutoEncoders take inputs as target values since
they are learning identity function, which is regarded as
unsupervised learning, but can such method be applied to
Convolutional Neural Networks for which the first hidden layer is
feature map? Each feature map is created by convolving a learned
kernel with a receptive field in the image. This learned kernel, how
could this be obtained by pre-training (unsupervised fashion)?
One thing to note is that autoencoders try to learn the non-trivial identify function, not the identify function itself. Otherwise they wouldn't have been useful at all. Well the pre-training helps moving the weight vectors towards a good starting point on the error surface. Then the backpropagation algorithm, which is basically doing gradient descent, is used improve upon those weights. Note that gradient descent gets stuck in the closes local minima.
[Ignore the term Global Minima in the image posted and think of it as another, better, local minima]
Intuitively speaking, suppose you are looking for an optimal path to get from origin A to destination B. Having a map with no routes shown on it (the errors you obtain at the last layer of the neural network model) kind of tells you where to to go. But you may put yourself in a route which has a lot of obstacles, up hills and down hills. Then suppose someone tells you about a route a a direction he has gone through before (the pre-training) and hands you a new map (the pre=training phase's starting point).
This could be an intuitive reason on why starting with random weights and immediately start to optimize the model with backpropagation may not necessarily help you achieve the performance you obtain with a pre-trained model. However, note that many models achieving state-of-the-art results do not use pre-training necessarily and they may use the backpropagation in combination with other optimization methods (e.g. adagrad, RMSProp, Momentum and ...) to hopefully avoid getting stuck in a bad local minima.
Here's the source for the second image.
I don't know a lot about autoencoder theory, but I've done a bit of work with RBMs. What RBMs do is they predict what the probability is of seeing the specific type of data in order to get the weights initialized to the right ball park- it is considered an (unsupervised) probabilistic model, so you don't correct using the known labels. Basically, the idea here is that having a learning rate that is too big will never lead to convergence but having one that is too small will take forever to train. Thus, by "pretraining" in this way you find out the ball park of the weights and then can set the learning rate to be small in order to get them down to the optimal values.
As for the second question, no, you don't generally prelearn kernels, at least not in an unsupervised fashion. I suspect that what is meant by pretraining here is a bit different than in your first question- this is to say, that what is happening is that they are taking a pretrained model (say from model zoo) and fine tuning it with a new set of data.
Which model you use generally depends on the type of data you have and the task at hand. Convnets I've found to train faster and efficiently, but not all data has meaning when convolved, in which case dbns may be the way to go. Unless say, you have a small amount of data then I'd use something other than neural networks entirely.
Anyways, I hope this helps clear some of your questions.
One of the most popular questions regarding Neural Networks seem to be:
Help!! My Neural Network is not converging!!
See here, here, here, here and here.
So after eliminating any error in implementation of the network, What are the most common things one should try??
I know that the things to try would vary widely depending on network architecture.
But tweaking which parameters (learning rate, momentum, initial weights, etc) and implementing what new features (windowed momentum?) were you able to overcome some similar problems while building your own neural net?
Please give answers which are language agnostic if possible. This question is intended to give some pointers to people stuck with neural nets which are not converging..
If you are using ReLU activations, you may have a "dying ReLU" problem. In short, under certain conditions, any neuron with a ReLU activation can be subject to a (bias) adjustment that leads to it never being activated ever again. It can be fixed with a "Leaky ReLU" activation, well explained in that article.
For example, I produced a simple MLP (3-layer) network with ReLU output which failed. I provided data it could not possibly fail on, and it still failed. I turned the learning rate way down, and it failed more slowly. It always converged to predicting each class with equal probability. It was all fixed by using a Leaky ReLU instead of standard ReLU.
If we are talking about classification tasks, then you should shuffle examples before training your net. I mean, don't feed your net with thousands examples of class #1, after thousands examples of class #2, etc... If you do that, your net most probably wouldn't converge, but would tend to predict last trained class.
I had faced this problem while implementing my own back prop neural network. I tried the following:
Implemented momentum (and kept the value at 0.5)
Kept the learning rate at 0.1
Charted the error, weights, input as well as output of each and every neuron, Seeing the data as a graph is more helpful in figuring out what is going wrong
Tried out different activation function (all sigmoid). But this did not help me much.
Initialized all weights to random values between -0.5 and 0.5 (My network's output was in the range -1 and 1)
I did not try this but Gradient Checking can be helpful as well
If the problem is only convergence (not the actual "well trained network", which is way to broad problem for SO) then the only thing that can be the problem once the code is ok is the training method parameters. If one use naive backpropagation, then these parameters are learning rate and momentum. Nothing else matters, as for any initialization, and any architecture, correctly implemented neural network should converge for a good choice of these two parameters (in fact, for momentum=0 it should converge to some solution too, for a small enough learning rate).
In particular - there is a good heuristic approach called "resillient backprop" which is in fact parameterless appraoch, which should (almost) always converge (assuming correct implementation).
after you've tried different meta parameters (optimization / architecture), the most probable place to look at is - THE DATA
as for myself - to minimize fiddling with meta parameters, i keep my optimizer automated - Adam is by opt-of-choice.
there are some rules of thumb regarding application vs architecture... but its really best to crunch those on your own.
to the point:
in my experience, after you've debugged the net (the easy debugging), and still don't converge or get to an undesired local minima, the usual suspect is the data.
weather you have contradictory samples or just incorrect ones (outliers), a small amount can make the difference from say 0.6-acc to (after cleaning) 0.9-acc..
a smaller but golden (clean) dataset is much better than a big slightly dirty one...
with augmentation you can tweak results even further.
The motivating idea behind neural nets seems to be that they learn the "right" features to apply logistic regression to. Is there a similar approach for linear regression? (or just regression problems in general?)
Would doing the obvious thing of removing the application of a sigmoid function for all neurons (ie, including the hidden layers) make sense/work? (ie, each neuron is performing linear regression instead of logistic regression).
Alternatively, would doing the (maybe even more obvious) thing of just scaling output values to [0,1] work? (intuitively I would think not, as the sigmoid function seems like it would cause the net to arbitrarily favor extreme values) (edit: though I was just searching around some more, and saw that one technique is to scale based on mean and variance, which seems like it might deal with this issue -- so maybe this is more viable than I thought).
Or is there some other technique for doing "feature learning" for regression problems?
Check out this applet. Try to learn different functions. When you dictate linear activation functions at both hidden and output layers, it even fails to learn the quadratic function. At least one layer needs to be set to sigmoid function, see figures below.
There are different kinds of scaling. Standard scaling, as you mentioned, eliminates the impact of mean and standard deviation of the training sample, is most often used in machine learning. Just make sure you are using the same mean and std value from training sample in the test sample.
The reason why scaling is required is because the output of sigmoid function ranges at (0,1). I didn't try, but I think it is better to scale the output even if you select linear function at output layer. Otherwise large input at hidden layer (with sigmoid) won't lead to drastic output (the sigmoid function is approximately linear when the input is at a small range, out of such range will make the output changes much slowly). You can try this by yourself in your own data.
Besides, if you have various features, the feature normalization that makes different features in the same scale is also recommended. The scaling speeds up gradient descent by avoiding many extra iterations that are required when one or more features take on much larger values than the rest.
As #Ray mentioned, deep learning that many levels of features are involved can help you with the feature learning, it's not all linear combinations though.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
This question does not appear to be about programming within the scope defined in the help center.
Closed 2 years ago.
Improve this question
Why do we have to normalize the input for a neural network?
I understand that sometimes, when for example the input values are non-numerical a certain transformation must be performed, but when we have a numerical input? Why the numbers must be in a certain interval?
What will happen if the data is not normalized?
It's explained well here.
If the input variables are combined linearly, as in an MLP [multilayer perceptron], then it is
rarely strictly necessary to standardize the inputs, at least in theory. The
reason is that any rescaling of an input vector can be effectively undone by
changing the corresponding weights and biases, leaving you with the exact
same outputs as you had before. However, there are a variety of practical
reasons why standardizing the inputs can make training faster and reduce the
chances of getting stuck in local optima. Also, weight decay and Bayesian
estimation can be done more conveniently with standardized inputs.
In neural networks, it is good idea not just to normalize data but also to scale them. This is intended for faster approaching to global minima at error surface. See the following pictures:
Pictures are taken from the coursera course about neural networks. Author of the course is Geoffrey Hinton.
Some inputs to NN might not have a 'naturally defined' range of values. For example, the average value might be slowly, but continuously increasing over time (for example a number of records in the database).
In such case feeding this raw value into your network will not work very well. You will teach your network on values from lower part of range, while the actual inputs will be from the higher part of this range (and quite possibly above range, that the network has learned to work with).
You should normalize this value. You could for example tell the network by how much the value has changed since the previous input. This increment usually can be defined with high probability in a specific range, which makes it a good input for network.
There are 2 Reasons why we have to Normalize Input Features before Feeding them to Neural Network:
Reason 1: If a Feature in the Dataset is big in scale compared to others then this big scaled feature becomes dominating and as a result of that, Predictions of the Neural Network will not be Accurate.
Example: In case of Employee Data, if we consider Age and Salary, Age will be a Two Digit Number while Salary can be 7 or 8 Digit (1 Million, etc..). In that Case, Salary will Dominate the Prediction of the Neural Network. But if we Normalize those Features, Values of both the Features will lie in the Range from (0 to 1).
Reason 2: Front Propagation of Neural Networks involves the Dot Product of Weights with Input Features. So, if the Values are very high (for Image and Non-Image Data), Calculation of Output takes a lot of Computation Time as well as Memory. Same is the case during Back Propagation. Consequently, Model Converges slowly, if the Inputs are not Normalized.
Example: If we perform Image Classification, Size of Image will be very huge, as the Value of each Pixel ranges from 0 to 255. Normalization in this case is very important.
Mentioned below are the instances where Normalization is very important:
K-Means
K-Nearest-Neighbours
Principal Component Analysis (PCA)
Gradient Descent
When you use unnormalized input features, the loss function is likely to have very elongated valleys. When optimizing with gradient descent, this becomes an issue because the gradient will be steep with respect some of the parameters. That leads to large oscillations in the search space, as you are bouncing between steep slopes. To compensate, you have to stabilize optimization with small learning rates.
Consider features x1 and x2, where range from 0 to 1 and 0 to 1 million, respectively. It turns out the ratios for the corresponding parameters (say, w1 and w2) will also be large.
Normalizing tends to make the loss function more symmetrical/spherical. These are easier to optimize because the gradients tend to point towards the global minimum and you can take larger steps.
Looking at the neural network from the outside, it is just a function that takes some arguments and produces a result. As with all functions, it has a domain (i.e. a set of legal arguments). You have to normalize the values that you want to pass to the neural net in order to make sure it is in the domain. As with all functions, if the arguments are not in the domain, the result is not guaranteed to be appropriate.
The exact behavior of the neural net on arguments outside of the domain depends on the implementation of the neural net. But overall, the result is useless if the arguments are not within the domain.
I believe the answer is dependent on the scenario.
Consider NN (neural network) as an operator F, so that F(input) = output. In the case where this relation is linear so that F(A * input) = A * output, then you might choose to either leave the input/output unnormalised in their raw forms, or normalise both to eliminate A. Obviously this linearity assumption is violated in classification tasks, or nearly any task that outputs a probability, where F(A * input) = 1 * output
In practice, normalisation allows non-fittable networks to be fittable, which is crucial to experimenters/programmers. Nevertheless, the precise impact of normalisation will depend not only on the network architecture/algorithm, but also on the statistical prior for the input and output.
What's more, NN is often implemented to solve very difficult problems in a black-box fashion, which means the underlying problem may have a very poor statistical formulation, making it hard to evaluate the impact of normalisation, causing the technical advantage (becoming fittable) to dominate over its impact on the statistics.
In statistical sense, normalisation removes variation that is believed to be non-causal in predicting the output, so as to prevent NN from learning this variation as a predictor (NN does not see this variation, hence cannot use it).
The reason normalization is needed is because if you look at how an adaptive step proceeds in one place in the domain of the function, and you just simply transport the problem to the equivalent of the same step translated by some large value in some direction in the domain, then you get different results. It boils down to the question of adapting a linear piece to a data point. How much should the piece move without turning and how much should it turn in response to that one training point? It makes no sense to have a changed adaptation procedure in different parts of the domain! So normalization is required to reduce the difference in the training result. I haven't got this written up, but you can just look at the math for a simple linear function and how it is trained by one training point in two different places. This problem may have been corrected in some places, but I am not familiar with them. In ALNs, the problem has been corrected and I can send you a paper if you write to wwarmstrong AT shaw.ca
On a high level, if you observe as to where normalization/standardization is mostly used, you will notice that, anytime there is a use of magnitude difference in model building process, it becomes necessary to standardize the inputs so as to ensure that important inputs with small magnitude don't loose their significance midway the model building process.
example:
√(3-1)^2+(1000-900)^2 ≈ √(1000-900)^2
Here, (3-1) contributes hardly a thing to the result and hence the input corresponding to these values is considered futile by the model.
Consider the following:
Clustering uses euclidean or, other distance measures.
NNs use optimization algorithm to minimise cost function(ex. - MSE).
Both distance measure(Clustering) and cost function(NNs) use magnitude difference in some way and hence standardization ensures that magnitude difference doesn't command over important input parameters and the algorithm works as expected.
Hidden layers are used in accordance with the complexity of our data. If we have input data which is linearly separable then we need not to use hidden layer e.g. OR gate but if we have a non linearly seperable data then we need to use hidden layer for example ExOR logical gate.
Number of nodes taken at any layer depends upon the degree of cross validation of our output.