I am reading A Tutorial on Energy Based Learning and I am trying to understand the difference between all those terms stated above in the context of SVMs. This link summarizes the differences between a loss, cost and an objective function. Based on my understanding,
Objective function: Something we want to minimize. For example ||w||^2 for SVM.
Loss function: Penalty between prediction and label which is also equivalent to the regularization term. Example is the hinge loss function in SVM.
Cost function: A general formulation that combines the objective and loss function.
Now, the 1st link states that the hinge function is max(0, m + E(W,Yi,Xi) - E(W,Y,X)) i.e. it is a function of the energy term. Does that mean that the energy function of the SVM is 1 - y(wx + b) ? Are energy functions are a part of a loss function. And a loss + objective function a part of the cost function ?
A concise summary of the 4 terms would immensely help my understanding. Also, do correct me if my understanding is wrong. The terms sound so confusing. Thanks !
Objective function: Something we want to minimize. For example ||w||^2 for SVM.
Objective function is - as name suggests - objective of optimization. It can be either something we want to minimize (like cost function) or maximize (like likelihood). In general - function that measures how good is our current solution (usually by returning a real number)
Loss function: Penalty between prediction and label which is also equivalent to the regularization term. Example is the hinge loss function in SVM.
First of all, loss is not equivalent to regularization, in any sense. Loss function is a a penalty between a model and truth. This can be a prediction of class conditional distribuition vs true label, thus can also be a data distribution vs. empirical sample, and many more.
Regularization
Regularization is a term, penalty, measure which is supposed to be a penalty for too complex model. In ML, or generally in statistics when dealing with estimators, you always try to balance two sources of error - variance (coming from too complex models, overfitting) and bias (coming from too simple models, bad learning methods, underfitting). Regularization is a technique of penalizing high-variance models in the optimization process in order to get less overfitted one. In other words - for techniques which can fit training set perfectly, it is important to have a measure which forbids it in order to preserve ability to generalize.
Cost function: A general formulation that combines the objective and loss function.
Cost function is just an objective function which one minimizes. It can be composed of some agglomeration of loss functions and regularizers.
Now, the 1st link states that the hinge function is max(0, m + E(W,Yi,Xi) - E(W,Y,X)) i.e. it is a function of the energy term. Does that mean that the energy function of the SVM is 1 - y(wx + b) ? Are energy functions are a part of a loss function. And a loss + objective function a part of the cost function ?
The hinge loss is max(0, 1 - y(<w,x> - b)). The one defined here is not really for SVM but for general factor graphs, I would strongly suggest to start learning ML from basics and not from advanced techniques. Without good understanding of basics of ML, this paper will not be possible to understand.
To show example with SVM and naming convention
C SUM_i=1^N max(0, 1 - y_i(<w, x_i> - b)) + ||w||^2
\__________________________/ \_____/
loss regularization
\_________________________________________________/
cost / objective function
Related
NOTE: when you see (0) in the functions it represents Theta not Zero
I've been studying Andrew Ng's Machine Learning Course, and I have the following inquery:
(Short Version: If one were to look at all the mathematical expressions/calculations used for both Forward AND Backward propagation, then it appears to me that we never use the Cost Function directly, but its Derivative , so what is the importance of the cost function and its choice anyway? is it purely to evaluate our system whenever we feel like it?)
Andrew mentioned that for Logistic Regression, using the MSE (Mean Squared Error) Cost function
wouldn't be good, because applying it to our Sigmoid function would yield a non-convex cost function that has a lot of Local Optima, so it is best that we use the following logistic cost function:
Which will have 2 graphs (one for y=0 and one for y=1), both of which are convex.
My question is the following, since it is our objective to minimize the cost function (aka have the Derivative reach 0), which we achieve by using Gradient Descent, updating our weights using the Derivative of the Cost Function, which in both cases (both cost functions) is the same derivative:
dJ = (h0(x(i)) - y(i)) . x(i)
So how did the different choice of cost function in this case effect our algorithm in any way? because in forward propagation, all we need is
h0(x(i)) = Sigmoid(0Tx)
which can be calculated without ever needing to calculate the cost function, then in backward propagation and in updating the weights, we always use the derivative of the cost function, so when does the Cost Function itself come into play? is it just necessary when we want an indication of how well our network is doing? (then why not just depend on the derivative to know that)
The forward propagation does not need the cost function in any way because you just applying all your learned weights to the corresponding input.
The cost function is generally used to measure how good your algorihm is by comparing your models outcome (therefore applying your current weights to your input) with the true label of the input (in supervised algorithms). The main objective is therefore to minimize the cost function error as (in most cases) you want the difference of the prediction and the true label as small as possible. In optimization it is pretty helpful if your function you want to optimize is convex because it guarantees that if you find a local minimum it is at the same time the global minimum.
For minimizing the cost function, gradient descent is used to iteratively update your weights to get closer to the minimum. This is done w.r.t to the learned weights such that you are able to update your weights of the model for achieving the lowest possible costs. The backpropagation algorithm is used to adjust the weights using the cost function in the backward pass.
Technically, you are correct: we do not explicitly use the cost function in any of the calculations for forward propagation and back propagation.
You asked 'what is the importance of the cost function and its choice anyway?'. I have two answers:
The cost function is incredibly important because its gradient is what allows us to update our weights. Although we are only actually computing the gradient of the cost function and not the cost function itself, choosing a different cost function would mean we would have a different gradient, thus changing how we update our weights.
The cost function allows us to evaluate our model performance. It is common practice to plot cost vs epoch to understand how the cost decreases over time.
Your answer indicted you essentially understood all of this already but I hoped to clarify it a bit. Thanks!
I know that GBtree uses a decision tree for classification and regression,
but how can we use gblinear for classification problem? Doesn't it gives us a continuous prediction?
I think I am confused between the parameters "boosters" and "objective function" in xgboost.
What can GBtree gives us compare to GBLinear ?
What is the difference between "Objective Function" to "Booster"
in xgboost?
GBLinear gives a "linear" modeling to solve your problem. Linear
regression is a Linear model that predict a continues value as you
mentioned. But there are other Linear models like Logistic
Regression which predict a value between 0 to 1 (or a probability of
a classification problem). So if you use a booster of the GBLinear
type, you should use binary:logistic objective function. GBtree gives a decision tree modeling to your problem.
Objective function is a function you try to minimize (it doesn't
directly relates to the model). Mostly, objective functions defines
some kind of error. For example, in a Linear Regression you have a
heuristic that looks as follows: Hw = w0 + w1*x1 + w2*x2 + ... +
wn*xn (this heuristic, is actually a way to model your
problem). Where the "Objective" also called the "Cost" function,
is similar to this: COST = (Hw - y_pred)^2. Your objective is to
find w0, ..., wn which will minimize that error thus you will get
a "model" that is "fit" to "solve" your problem.
GBtree / GBlinear are models. A way to model your problem. The model
worth nothing without "tuning" his "weights". With the "objective"
function, you "tune" your "weights".
I understand neural networks with any number of hidden layers can approximate nonlinear functions, however, can it approximate:
f(x) = x^2
I can't think of how it could. It seems like a very obvious limitation of neural networks that can potentially limit what it can do. For example, because of this limitation, neural networks probably can't properly approximate many functions used in statistics like Exponential Moving Average, or even variance.
Speaking of moving average, can recurrent neural networks properly approximate that? I understand how a feedforward neural network or even a single linear neuron can output a moving average using the sliding window technique, but how would recurrent neural networks do it without X amount of hidden layers (X being the moving average size)?
Also, let us assume we don't know the original function f, which happens to get the average of the last 500 inputs, and then output a 1 if it's higher than 3, and 0 if it's not. But for a second, pretend we don't know that, it's a black box.
How would a recurrent neural network approximate that? We would first need to know how many timesteps it should have, which we don't. Perhaps a LSTM network could, but even then, what if it's not a simple moving average, it's an exponential moving average? I don't think even LSTM can do it.
Even worse still, what if f(x,x1) that we are trying to learn is simply
f(x,x1) = x * x1
That seems very simple and straightforward. Can a neural network learn it? I don't see how.
Am I missing something huge here or are machine learning algorithms extremely limited? Are there other learning techniques besides neural networks that can actually do any of this?
The key point to understand is compact:
Neural networks (as any other approximation structure like, polynomials, splines, or Radial Basis Functions) can approximate any continuous function only within a compact set.
In other words the theory states that, given:
A continuous function f(x),
A finite range for the input x, [a,b], and
A desired approximation accuracy ε>0,
then there exists a neural network that approximates f(x) with an approximation error less than ε, everywhere within [a,b].
Regarding your example of f(x) = x2, yes you can approximate it with a neural network within any finite range: [-1,1], [0, 1000], etc. To visualise this, imagine that you approximate f(x) within [-1,1] with a Step Function. Can you do it on paper? Note that if you make the steps narrow enough you can achieve any desired accuracy. The way neural networks approximate f(x) is not much different than this.
But again, there is no neural network (or any other approximation structure) with a finite number of parameters that can approximate f(x) = x2 for all x in [-∞, +∞].
The question is very legitimate and unfortunately many of the answers show how little practitioners seem to know about the theory of neural networks. The only rigorous theorem that exists about the ability of neural networks to approximate different kinds of functions is the Universal Approximation Theorem.
The UAT states that any continuous function on a compact domain can be approximated by a neural network with only one hidden layer provided the activation functions used are BOUNDED, continuous and monotonically increasing. Now, a finite sum of bounded functions is bounded by definition.
A polynomial is not bounded so the best we can do is provide a neural network approximation of that polynomial over a compact subset of R^n. Outside of this compact subset, the approximation will fail miserably as the polynomial will grow without bound. In other words, the neural network will work well on the training set but will not generalize!
The question is neither off-topic nor does it represent the OP's opinion.
I am not sure why there is such a visceral reaction, I think it is a legitimate question that is hard to find by googling it, even though I think it is widely appreciated and repeated outloud. I think in this case you are looking for the actually citations showing that a neural net can approximate any function. This recent paper explains it nicely, in my opinion. They also cite the original paper by Barron from 1993 that proved a less general result. The conclusion: a two-layer neural network can represent any bounded degree polynomial, under certain (seemingly non-restrictive) conditions.
Just in case the link does not work, it is called "Learning Polynomials with Neural Networks" by Andoni et al., 2014.
I understand neural networks with any number of hidden layers can approximate nonlinear functions, however, can it approximate:
f(x) = x^2
The only way I can make sense of that question is that you're talking about extrapolation. So e.g. given training samples in the range -1 < x < +1 can a neural network learn the right values for x > 100? Is that what you mean?
If you had prior knowledge, that the functions you're trying to approximate are likely to be low-order polynomials (or any other set of functions), then you could surely build a neural network that can represent these functions, and extrapolate x^2 everywhere.
If you don't have prior knowledge, things are a bit more difficult: There are infinitely many smooth functions that fit x^2 in the range -1..+1 perfectly, and there's no good reason why we would expect x^2 to give better predictions than any other function. In other words: If we had no prior knowledge about the function we're trying to learn, why would we want to learn x -> x^2? In the realm of artificial training sets, x^2 might be a likely function, but in the real world, it probably isn't.
To give an example: Let's say the temperature on Monday (t=0) is 0°, on Tuesday it's 1°, on Wednesday it's 4°. We have no reason to believe temperatures behave like low-order polynomials, so we wouldn't want to infer from that data that the temperature next Monday will probably be around 49°.
Also, let us assume we don't know the original function f, which happens to get the average of the last 500 inputs, and then output a 1 if it's higher than 3, and 0 if it's not. But for a second, pretend we don't know that, it's a black box.
How would a recurrent neural network approximate that?
I think that's two questions: First, can a neural network represent that function? I.e. is there a set of weights that would give exactly that behavior? It obviously depends on the network architecture, but I think we can come up with architectures that can represent (or at least closely approximate) this kind of function.
Question two: Can it learn this function, given enough training samples? Well, if your learning algorithm doesn't get stuck in a local minimum, sure: If you have enough training samples, any set of weights that doesn't approximate your function gives a training error greater that 0, while a set of weights that fit the function you're trying to learn has a training error=0. So if you find a global optimum, the network must fit the function.
A network can learn x|->x * x if it has a neuron that calculates x * x. Or more generally, a node that calculates x**p and learns p. These aren't commonly used, but the statement that "no neural network can learn..." is too strong.
A network with ReLUs and a linear output layer can learn x|->2*x, even on an unbounded range of x values. The error will be unbounded, but the proportional error will be bounded. Any function learnt by such a network is piecewise linear, and in particular asymptotically linear.
However, there is a risk with ReLUs: once a ReLU is off for all training examples it ceases learning. With a large domain, it will turn on for some possible test examples, and give an erroneous result. So ReLUs are only a good choice if test cases are likely to be within the convex hull of the training set. This is easier to guarantee if the dimensionality is low. One work around is to prefer LeakyReLU.
One other issue: how many neurons do you need to achieve the approximation you want? Each ReLU or LeakyReLU implements a single change of gradient. So the number needed depends on the maximum absolute value of the second differential of the objective function, divided by the maximum error to be tolerated.
There are theoretical limitations of Neural Networks. No neural network can ever learn the function f(x) = x*x
Nor can it learn an infinite number of other functions, unless you assume the impractical:
1- an infinite number of training examples
2- an infinite number of units
3- an infinite amount of time to converge
NNs are good in learning low-level pattern recognition problems (signals that in the end have some statistical pattern that can be represented by some "continuous" function!), but that's it!
No more!
Here's a hint:
Try to build a NN that takes n+1 data inputs (x0, x1, x2, ... xn) and it will return true (or 1) if (2 * x0) is in the rest of the sequence. And, good luck.
Infinite functions especially those that are recursive cannot be learned. They just are!
Im personally studying theories of neural network and got some questions.
In many books and references, for activation function of hidden layer, hyper-tangent functions were used.
Books came up with really simple reason that linear combinations of tanh functions can describe nearly all shape of functions with given error.
But, there came a question.
Is this a real reason why tanh function is used?
If then, is it the only reason why tanh function is used?
if then, is tanh function the only function that can do that?
if not, what is the real reason?..
I stock here keep thinking... please help me out of this mental(?...) trap!
Most of time tanh is quickly converge than sigmoid and logistic function, and performs better accuracy [1]. However, recently rectified linear unit (ReLU) is proposed by Hinton [2] which shows ReLU train six times fast than tanh [3] to reach same training error. And you can refer to [4] to see what benefits ReLU provides.
Accordining to about 2 years machine learning experience. I want to share some stratrgies the most paper used and my experience about computer vision.
Normalizing input is very important
Normalizing well could get better performance and converge quickly. Most of time we will subtract mean value to make input mean to be zero to prevent weights change same directions so that converge slowly [5] .Recently google also points that phenomenon as internal covariate shift out when training deep learning, and they proposed batch normalization [6] so as to normalize each vector having zero mean and unit variance.
More data more accuracy
More training data could generize feature space well and prevent overfitting. In computer vision if training data is not enough, most of used skill to increase training dataset is data argumentation and synthesis training data.
Choosing a good activation function allows training better and efficiently.
ReLU nonlinear acitivation worked better and performed state-of-art results in deep learning and MLP. Moreover, it has some benefits e.g. simple to implementation and cheaper computation in back-propagation to efficiently train more deep neural net. However, ReLU will get zero gradient and do not train when the unit is zero active. Hence some modified ReLUs are proposed e.g. Leaky ReLU, and Noise ReLU, and most popular method is PReLU [7] proposed by Microsoft which generalized the traditional recitifed unit.
Others
choose large initial learning rate if it will not oscillate or diverge so as to find a better global minimum.
shuffling data
In truth both tanh and logistic functions can be used. The idea is that you can map any real number ( [-Inf, Inf] ) to a number between [-1 1] or [0 1] for the tanh and logistic respectively. In this way, it can be shown that a combination of such functions can approximate any non-linear function.
Now regarding the preference for the tanh over the logistic function is that the first is symmetric regarding the 0 while the second is not. This makes the second one more prone to saturation of the later layers, making training more difficult.
To add up to the the already existing answer, the preference for symmetry around 0 isn't just a matter of esthetics. An excellent text by LeCun et al "Efficient BackProp" shows in great details why it is a good idea that the input, output and hidden layers have mean values of 0 and standard deviation of 1.
Update in attempt to appease commenters: based purely on observation, rather than the theory that is covered above, Tanh and ReLU activation functions are more performant than sigmoid. Sigmoid also seems to be more prone to local optima, or a least extended 'flat line' issues. For example, try limiting the number of features to force logic into network nodes in XOR and sigmoid rarely succeeds whereas Tanh and ReLU have more success.
Tanh seems maybe slower than ReLU for many of the given examples, but produces more natural looking fits for the data using only linear inputs, as you describe. For example a circle vs a square/hexagon thing.
http://playground.tensorflow.org/ <- this site is a fantastic visualisation of activation functions and other parameters to neural network. Not a direct answer to your question but the tool 'provides intuition' as Andrew Ng would say.
Many of the answers here describe why tanh (i.e. (1 - e^2x) / (1 + e^2x)) is preferable to the sigmoid/logistic function (1 / (1 + e^-x)), but it should noted that there is a good reason why these are the two most common alternatives that should be understood, which is that during training of an MLP using the back propagation algorithm, the algorithm requires the value of the derivative of the activation function at the point of activation of each node in the network. While this could generally be calculated for most plausible activation functions (except those with discontinuities, which is a bit of a problem for those), doing so often requires expensive computations and/or storing additional data (e.g. the value of input to the activation function, which is not otherwise required after the output of each node is calculated). Tanh and the logistic function, however, both have very simple and efficient calculations for their derivatives that can be calculated from the output of the functions; i.e. if the node's weighted sum of inputs is v and its output is u, we need to know du/dv which can be calculated from u rather than the more traditional v: for tanh it is 1 - u^2 and for the logistic function it is u * (1 - u). This fact makes these two functions more efficient to use in a back propagation network than most alternatives, so a compelling reason would usually be required to deviate from them.
In theory I in accord with above responses. In my experience, some problems have a preference for sigmoid rather than tanh, probably due to the nature of these problems (since there are non-linear effects, is difficult understand why).
Given a problem, I generally optimize networks using a genetic algorithm. The activation function of each element of the population is choosen randonm between a set of possibilities (sigmoid, tanh, linear, ...). For a 30% of problems of classification, best element found by genetic algorithm has sigmoid as activation function.
In deep learning the ReLU has become the activation function of choice because the math is much simpler from sigmoid activation functions such as tanh or logit, especially if you have many layers. To assign weights using backpropagation, you normally calculate the gradient of the loss function and apply the chain rule for hidden layers, meaning you need the derivative of the activation functions. ReLU is a ramp function where you have a flat part where the derivative is 0, and a skewed part where the derivative is 1. This makes the math really easy. If you use the hyperbolic tangent you might run into the fading gradient problem, meaning if x is smaller than -2 or bigger than 2, the derivative gets really small and your network might not converge, or you might end up having a dead neuron that does not fire anymore.
I'm going through the ML Class on Coursera on Logistic Regression and also the Manning Book Machine Learning in Action. I'm trying to learn by implementing everything in Python.
I'm not able to understand the difference between the cost function and the gradient. There are examples on the net where people compute the cost function and then there are places where they don't and just go with the gradient descent function w :=w - (alpha) * (delta)w * f(w).
What is the difference between the two if any?
Whenever you train a model with your data, you are actually producing some new values (predicted) for a specific feature. However, that specific feature already has some values which are real values in the dataset. We know the closer the predicted values to their corresponding real values, the better the model.
Now, we are using cost function to measure how close the predicted values are to their corresponding real values.
We also should consider that the weights of the trained model are responsible for accurately predicting the new values. Imagine that our model is y = 0.9*X + 0.1, the predicted value is nothing but (0.9*X+0.1) for different Xs.
[0.9 and 0.1 in the equation are just random values to understand.]
So, by considering Y as real value corresponding to this x, the cost formula is coming to measure how close (0.9*X+0.1) is to Y.
We are responsible for finding the better weight (0.9 and 0.1) for our model to come up with a lowest cost (or closer predicted values to real ones).
Gradient descent is an optimization algorithm (we have some other optimization algorithms) and its responsibility is to find the minimum cost value in the process of trying the model with different weights or indeed, updating the weights.
We first run our model with some initial weights and gradient descent updates our weights and find the cost of our model with those weights in thousands of iterations to find the minimum cost.
One point is that gradient descent is not minimizing the weights, it is just updating them. This algorithm is looking for minimum cost.
A cost function is something you want to minimize. For example, your cost function might be the sum of squared errors over your training set. Gradient descent is a method for finding the minimum of a function of multiple variables. So you can use gradient descent to minimize your cost function. If your cost is a function of K variables, then the gradient is the length-K vector that defines the direction in which the cost is increasing most rapidly. So in gradient descent, you follow the negative of the gradient to the point where the cost is a minimum. If someone is talking about gradient descent in a machine learning context, the cost function is probably implied (it is the function to which you are applying the gradient descent algorithm).
It's strange to think about it, but there is more than one measure for how "accurately" a line fits to data points.
To access how accurately a line fits the data, we have a "cost" function which which can compare predicted vs. actual values and provide a "penalty" for how wrong it is.
penalty = cost_funciton(predicted, actual)
A naive cost function might just take the difference between the predicted and actual.
More sophisticated functions will square the value, since we'd rather have many small errors than one large error.
Additionally, each point has a different "sensitivity" to moving the line. Some points react very strongly to movement. Others react less strongly.
Often, you can make a tradeoff, and move TOWARD a point that is sensitive, and AWAY from a point that is NOT sensitive. In that scenario , you get more than you give up.
The "gradient" is a way of measuring how sensitive each point is to moving the line.
This article does a good job of describing WHY there is more than one measure, and WHY some points are more sensitive than others:
https://towardsdatascience.com/wrapping-your-head-around-gradient-descent-with-pictures-3fbd810235f5?source=friends_link&sk=7117e5de8c66bd4a4c2bb2a87a928773
Let's take an example of logistic regression model for binary classification. Output(Predicted Value) of the model for any given input will be offset(deviation) with respect to the actual output(Expected Value) while training. So, the model needs to be trained with minimal error(loss) so that model can perform well with high accuracy.
The function used to find the parameters(m and c in case of linear equation, y = mx+c) value at which the minimal error(loss) occurs is called Cost Function/Loss Function. Loss function is a term used to find the loss for single row/record of the training sample and Cost function is a term used to find the loss for the entire training dataset.
Now, How do we find the parameter(m and c in our case) values at which the minimum loss occurs? Its by using gradient descent algorithm using the equation, which helps us to find the points at which the minimum loss occurs and the parameters values at this points are considered for model building (let say y = 0.5x + 2) where m=.5 and c=2 are the points at which the loss is minimum.
Cost function is something is like at what cost you are building your model for a good model that cost should be minimum. To find the minimum cost function we use gradient descent method. That give value of coefficients to determine minimum cost function