I am using feed forward, gradient descent backpropagation neural networks.
Currently I have only worked with non-linear networks where tanh is activation function.
I was wondering.
What kind of tasks would you give to a neural networks with non-linear activation function and what kind of tasks for linear?
I know that network with linear activation function are used to solve linear problems.
What are those linear problems?
Any examples?
Thanks!
I'd say never, since composition of linear functions is still linear using a neural network with linear activations is just a way to complicate linear regression.
Whether to choose a linear model or something more complicated is up to you and depends on the data you have; this is (one of the reasons) why it is customary hold out some data during training and use it to validate the model. Other ways of testing models are residuals analysis, hypothesis testing, and so on
Related
I understand all the computational steps of training a neural network with gradient descent using forwardprop and backprop, but I'm trying to wrap my head around why they work so much better than logistic regression.
For now all I can think of is:
A) the neural network can learn it's own parameters
B) there are many more weights than simple logistic regression thus allowing for more complex hypotheses
Can someone explain why a neural network works so well in general? I am a relative beginner.
Neural Networks can have a large number of free parameters (the weights and biases between interconnected units) and this gives them the flexibility to fit highly complex data (when trained correctly) that other models are too simple to fit. This model complexity brings with it the problems of training such a complex network and ensuring the resultant model generalises to the examples it’s trained on (typically neural networks require large volumes of training data, that other models don't).
Classically logistic regression has been limited to binary classification using a linear classifier (although multi-class classification can easily be achieved with one-vs-all, one-vs-one approaches etc. and there are kernalised variants of logistic regression that allow for non-linear classification tasks). In general therefore, logistic regression is typically applied to more simple, linearly-separable classification tasks, where small amounts of training data are available.
Models such as logistic regression and linear regression can be thought of as simple multi-layer perceptrons (check out this site for one explanation of how).
To conclude, it’s the model complexity that allows neural nets to solve more complex classification tasks, and to have a broader application (particularly when applied to raw data such as image pixel intensities etc.), but their complexity means that large volumes of training data are required and training them can be a difficult task.
Recently Dr. Naftali Tishby's idea of Information Bottleneck to explain the effectiveness of deep neural networks is making the rounds in the academic circles.
His video explaining the idea (link below) can be rather dense so I'll try to give the distilled/general form of the core idea to help build intuition
https://www.youtube.com/watch?v=XL07WEc2TRI
To ground your thinking, vizualize the MNIST task of classifying the digit in the image. For this, I am only talking about simple fully-connected neural networks (not Convolutional NN as is typically used for MNIST)
The input to a NN contains information about the output hidden inside of it. Some function is needed to transform the input to the output form. Pretty obvious.
The key difference in thinking needed to build better intuition is to think of the input as a signal with "information" in it (I won't go into information theory here). Some of this information is relevant for the task at hand (predicting the output). Think of the output as also a signal with a certain amount of "information". The neural network tries to "successively refine" and compress the input signal's information to match the desired output signal. Think of each layer as cutting away at the unneccessary parts of the input information, and
keeping and/or transforming the output information along the way through the network.
The fully-connected neural network will transform the input information into a form in the final hidden layer, such that it is linearly separable by the output layer.
This is a very high-level and fundamental interpretation of the NN, and I hope it will help you see it clearer. If there are parts you'd like me to clarify, let me know.
There are other essential pieces in Dr.Tishby's work, such as how minibatch noise helps training, and how the weights of a neural network layer can be seen as doing a random walk within the constraints of the problem.
These parts are a little more detailed, and I'd recommend first toying with neural networks and taking a course on Information Theory to help build your understanding.
Consider you have a large dataset and you want to build a binary classification model for that, Now you have two options that you have pointed out
Logistic Regression
Neural Networks ( Consider FFN for now )
Each node in a neural network will be associated with an activation function for example let's choose Sigmoid since Logistic regression also uses sigmoid internally to make decision.
Let's see how the decision of logistic regression looks when applied on the data
See some of the green spots present in the red boundary?
Now let's see the decision boundary of neural network (Forgive me for using a different color)
Why this happens? Why does the decision boundary of neural network is so flexible which gives more accurate results than Logistic regression?
or the question you asked is "Why neural networks works so well ?" is because of it's hidden units or hidden layers and their representation power.
Let me put it this way.
You have a logistic regression model and a Neural network which has say 100 neurons each of Sigmoid activation. Now each neuron will be equivalent to one logistic regression.
Now assume a hundred logistic units trained together to solve one problem versus one logistic regression model. Because of these hidden layers the decision boundary expands and yields better results.
While you are experimenting you can add more number of neurons and see how the decision boundary is changing. A logistic regression is same as a neural network with single neuron.
The above given is just an example. Neural networks can be trained to get very complex decision boundaries
Neural networks allow the person training them to algorithmically discover features, as you pointed out. However, they also allow for very general nonlinearity. If you wish, you can use polynomial terms in logistic regression to achieve some degree of nonlinearity, however, you must decide which terms you will use. That is you must decide a priori which model will work. Neural networks can discover the nonlinear model that is needed.
'Work so well' depends on the concrete scenario. Both of them do essentially the same thing: predicting.
The main difference here is neural network can have hidden nodes for concepts, if it's propperly set up (not easy), using these inputs to make the final decission.
Whereas linear regression is based on more obvious facts, and not side effects. A neural network should de able to make more accurate predictions than linear regression.
Neural networks excel at a variety of tasks, but to get an understanding of exactly why, it may be easier to take a particular task like classification and dive deeper.
In simple terms, machine learning techniques learn a function to predict which class a particular input belongs to, depending on past examples. What sets neural nets apart is their ability to construct these functions that can explain even complex patterns in the data. The heart of a neural network is an activation function like Relu, which allows it to draw some basic classification boundaries like:
Example classification boundaries of Relus
By composing hundreds of such Relus together, neural networks can create arbitrarily complex classification boundaries, for example:
Composing classification boundaries
The following article tries to explain the intuition behind how neural networks work: https://medium.com/machine-intelligence-report/how-do-neural-networks-work-57d1ab5337ce
Before you step into neural network see if you have assessed all aspects of normal regression.
Use this as a guide
and even before you discard normal regression - for curved type of dependencies - you should strongly consider kernels with SVM
Neural networks are defined with an objective and loss function. The only process that happens within a neural net is to optimize for the objective function by reducing the loss function or error. The back propagation helps in finding the optimized objective function and reach our output with an output condition.
My colleague and I are trying to wrap our heads around the difference between logistic regression and an SVM. Clearly they are optimizing different objective functions. Is an SVM as simple as saying it's a discriminative classifier that simply optimizes the hinge loss? Or is it more complex than that? How do the support vectors come into play? What about the slack variables? Why can't you have deep SVM's the way you can't you have a deep neural network with sigmoid activation functions?
I will answer one thing at at time
Is an SVM as simple as saying it's a discriminative classifier that simply optimizes the hinge loss?
SVM is simply a linear classifier, optimizing hinge loss with L2 regularization.
Or is it more complex than that?
No, it is "just" that, however there are different ways of looking at this model leading to complex, interesting conclusions. In particular, this specific choice of loss function leads to extremely efficient kernelization, which is not true for log loss (logistic regression) nor mse (linear regression). Furthermore you can show very important theoretical properties, such as those related to Vapnik-Chervonenkis dimension reduction leading to smaller chance of overfitting.
Intuitively look at these three common losses:
hinge: max(0, 1-py)
log: y log p
mse: (p-y)^2
Only the first one has the property that once something is classified correctly - it has 0 penalty. All the remaining ones still penalize your linear model even if it classifies samples correctly. Why? Because they are more related to regression than classification they want a perfect prediction, not just correct.
How do the support vectors come into play?
Support vectors are simply samples placed near the decision boundary (losely speaking). For linear case it does not change much, but as most of the power of SVM lies in its kernelization - there SVs are extremely important. Once you introduce kernel, due to hinge loss, SVM solution can be obtained efficiently, and support vectors are the only samples remembered from the training set, thus building a non-linear decision boundary with the subset of the training data.
What about the slack variables?
This is just another definition of the hinge loss, more usefull when you want to kernelize the solution and show the convexivity.
Why can't you have deep SVM's the way you can't you have a deep neural network with sigmoid activation functions?
You can, however as SVM is not a probabilistic model, its training might be a bit tricky. Furthermore whole strength of SVM comes from efficiency and global solution, both would be lost once you create a deep network. However there are such models, in particular SVM (with squared hinge loss) is nowadays often choice for the topmost layer of deep networks - thus the whole optimization is actually a deep SVM. Adding more layers in between has nothing to do with SVM or other cost - they are defined completely by their activations, and you can for example use RBF activation function, simply it has been shown numerous times that it leads to weak models (to local features are detected).
To sum up:
there are deep SVMs, simply this is a typical deep neural network with SVM layer on top.
there is no such thing as putting SVM layer "in the middle", as the training criterion is actually only applied to the output of the network.
using of "typical" SVM kernels as activation functions is not popular in deep networks due to their locality (as opposed to very global relu or sigmoid)
I'm trying to understand the difference between a restricted Boltzmann machine (RBM), and a feed-forward neural network (NN). I know that an RBM is a generative model, where the idea is to reconstruct the input, whereas an NN is a discriminative model, where the idea is the predict a label. But what I am unclear about, is why you cannot just use a NN for a generative model? In particular, I am thinking about deep belief networks and multi-layer perceptrons.
Suppose my input to the NN is a set of notes called x, and my output of the NN is a set of nodes y. In a discriminative model, my loss during training would be the difference between y, and the value of y that I want x to produce (e.g. ground truth probabilities for class labels). However, what about if I just made the output have the same number of nodes as the input, and then set the loss to be the difference between x and y? In this way, the network would learn to reconstruct the input, like in an RBM.
So, given that a NN (or a multi-layer perceptron) can be used to train a generative model in this way, why would you use an RBM (or a deep belief network) instead? Or in this case, would they be exactly the same?
You can use a NN for a generative model in exactly the way you describe. This is known as an autoencoder, and these can work quite well. In fact, these are often the building blocks of deep belief networks.
An RBM is a quite different model from a feed-forward neural network. They have connections going both ways (forward and backward) that have a probabilistic / energy interpretation. You'll need to read the details to understand.
A deep belief network (DBN) is just a neural network with many layers. This can be a large NN with layers consisting of a sort of autoencoders, or consist of stacked RBMs. You need special methods, tricks and lots of data for training these deep and large networks. Simple back-propagation suffers from the vanishing gradients problem. But if you do manage to train them, they can be very powerful (encode "higher level" concepts).
Hope this helps to point you in the right directions.
I am finding a very hard time to visualize how the activation function actually manages to classify non-linearly separable training data sets.
Why does the activation function (e.g tanh function) work for non-linear cases? What exactly happens mathematically when the activation function projects the input to output? What separates training samples of different classes, and how does this work if one had to plot this process graphically?
I've tried looking for numerous sources, but what exactly makes the activation function actually work for classifying training samples in a neural network, I just cannot grasp easily and would like to be able to picture this in my mind.
Mathematical result behind neural networks is Universal Approximation Theorem. Basically, sigmoidal functions (those which saturate on both ends, like tanh) are smooth almost-piecewise-constant approximators. The more neurons you have – the better your approximation is.
This picture was taked from this article: A visual proof that neural nets can compute any function. Make sure to check that article, it has other examples and interactive applets.
NNs actually, at each level, create new features by distorting input space. Non-linear functions allow you to change "curvature" of target function, so further layers have chance to make it linear-separable. If there were no non-linear functions, any combination of linear function is still linear, thus no benefit from multi-layerness. As a graphical example consider
this animation
This pictures where taken from this article. Also check out that cool visualization applet.
Activation functions have very little to do with classifying non-linearly separable sets of data.
Activation functions are used as a way to normalize signals at every step in your neural network. They typically have an infinite domain and a finite range. Tanh, for example, has a domain of (-∞,∞) and a range of (-1,1). The sigmoid function maps the same domain to (0,1).
You can think of this as a way of enforcing equality across all of your learned features at a given neural layer (a.k.a. feature scaling). Since the input domain is not known before hand it's not as simple as regular feature scaling (for linear regression) and thusly activation functions must be used. The effects of the activation function are compensated for when computing errors during back-propagation.
Back-propagation is a process that applies error to the neural network. You can think of this as a positive reward for the neurons that contributed to the correct classification and a negative reward for the neurons that contributed to an incorrect classification. This contribution is often known as the gradient of the neural network. The gradient is, effectively, a multi-variable derivative.
When back-propagating the error, each individual neuron's contribution to the gradient is the activations function's derivative at the input value for that neuron. Sigmoid is a particularly interesting function because its derivative is extremely cheap to compute. Specifically s'(x) = 1 - s(x); it was designed this way.
Here is an example image (found by google image searching: neural network classification) that demonstrates how a neural network might be superimposed on top of your data set:
I hope that gives you a relatively clear idea of how neural networks might classify non-linearly separable datasets.
I'm having trouble with some of the concepts in machine learning through neural networks. One of them is backpropagation. In the weight updating equation,
delta_w = a*(t - y)*g'(h)*x
t is the "target output", which would be your class label, or something, in the case of supervised learning. But what would the "target output" be for unsupervised learning?
Can someone kindly provide an example of how you'd use BP in unsupervised learning, specifically for clustering of classification?
Thanks in advance.
The most common thing to do is train an autoencoder, where the desired outputs are equal to the inputs. This makes the network try to learn a representation that best "compresses" the input distribution.
Here's a patent describing a different approach, where the output labels are assigned randomly and then sometimes flipped based on convergence rates. It seems weird to me, but okay.
I'm not familiar with other methods that use backpropogation for clustering or other unsupervised tasks. Clustering approaches with ANNs seem to use other algorithms (example 1, example 2).
I'm not sure which unsupervised machine learning algorithm uses backpropagation specifically; if there is one I haven't heard of it. Can you point to an example?
Backpropagation is used to compute the derivatives of the error function for training an artificial neural network with respect to the weights in the network. It's named as such because the "errors" are "propagating" through the network "backwards". You need it in this case because the final error with respect to the target depends on a function of functions (of functions ... depending on how many layers in your ANN.) The derivatives allow you to then adjust the values to improve the error function, tempered by the learning rate (this is gradient descent).
In unsupervised algorithms, you don't need to do this. For example, in k-Means, where you are trying to minimize the mean squared error (MSE), you can minimize the error directly at each step given the assignments; no gradients needed. In other clustering models, such as a mixture of Gaussians, the expectation-maximization (EM) algorithm is much more powerful and accurate than any gradient-descent based method.
What you might be asking is about unsupervised feature learning and deep learning.
Feature learning is the only unsupervised method I can think of with respect of NN or its recent variant.(a variant called mixture of RBM's is there analogous to mixture of gaussians but you can build a lot of models based on the two). But basically Two models I am familiar with are RBM's(restricted boltzman machines) and Autoencoders.
Autoencoders(optionally sparse activations can be encoded in optimization function) are just feedforward neural networks which tune its weights in such a way that the output is a reconstructed input. Multiple hidden layers can be used but the weight initialization uses a greedy layer wise training for better starting point. So to answer the question the target function will be input itself.
RBM's are stochastic networks usually interpreted as graphical model which has restrictions on connections. In this setting there is no output layer and the connection between input and latent layer is bidirectional like an undirected graphical model. What it tries to learn is a distribution on inputs(observed and unobserved variables). Here also your answer would be input is the target.
Mixture of RBM's(analogous to mixture of gaussians) can be used for soft clustering or KRBM(analogous to K-means) can be used for hard clustering. Which in effect feels like learning multiple non-linear subspaces.
http://deeplearning.net/tutorial/rbm.html
http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial
An alternative approach is to use something like generative backpropagation. In this scenario, you train a neural network updating the weights AND the input values. The given values are used as the output values since you can compute an error value directly. This approach has been used in dimensionality reduction, matrix completion (missing value imputation) among other applications. For more information, see non-linear principal component analysis (NLPCA) and unsupervised backpropagation (UBP) which uses the idea of generative backpropagation. UBP extends NLPCA by introducing a pre-training stage. An implementation of UBP and NLPCA and unsupervised backpropagation can be found in the waffles machine learning toolkit. The documentation for UBP and NLPCA can be found using the nlpca command.
To use back-propagation for unsupervised learning it is merely necessary to set t, the target output, at each stage of the algorithm to the class for which the average distance to each element of the class before updating is least. In short we always try to train the ANN to place its input into the class whose members are most similar in terms of our input. Because this process is sensitive to input scale it is necessary to first normalize the input data in each dimension by subtracting the average and dividing by the standard deviation for each component in order to calculate the distance in a scale-invariant manner.
The advantage to using a back-prop neural network rather than a simple distance from a center definition of the clusters is that neural networks can allow for more complex and irregular boundaries between clusters.