Questions tagged [activation-function]

For questions related to the selection of and theory behind specific activation functions used in artificial networks.

Filter by
Sorted by
Tagged with
2
votes
1answer
216 views

How do two perceptrons produce different linear decision boundaries when learning?

I've learned that you can use two perceptrons to ultimately create a classifier for non-linearly separable data. I'm trying to understand how / if these two perceptrons converge to two different ...
1
vote
0answers
36 views

How do I choose the activation function of the output layer of a neural network (based on theoretical motivations)?

Is there a method (not a table of recommendations!) that could tell me what activation function to choose if the outputs of the neural network have some interpretation? For example, these can be the ...
1
vote
1answer
46 views

Is it a great misconception that the softmax is an activation function?

An activation function is a function from $R \rightarrow R$. It takes as input the inner products of weights and activations in the previous layer. It outputs the activation. A softmax however, is a ...
7
votes
1answer
500 views

Why isn't the ElliotSig activation function widely used?

The Softsign (a.k.a. ElliotSig) activation function is really simple: $$ f(x) = \frac{x}{1+|x|} $$ It is bounded $[-1,1]$, has a first derivative, it is monotonic, and it is computationally ...
4
votes
1answer
632 views

What is a “logit probability”?

DeepMind's paper "Mastering the game of Go without human knowledge" states in its "Methods" section on its "Neural network architecture" that the output layer of AlphaGo Zero's policy head is "A fully ...
10
votes
1answer
2k views

What happens when I mix activation functions?

There are several activation functions, such as ReLU, sigmoid or $\tanh$. What happens when I mix activation functions? I recently found that Google has developed Swish activation function which is (...
1
vote
1answer
182 views

Method to compute the sum when the activation is a continuous function?

Background My understanding is the input neurons seem to seem to compute a weighted sum moving from one layer to another. $$ \sum_i a_i w_i = a'_{k} $$ But to compute this weighted sum the sum ...
0
votes
1answer
377 views

What is the derivative function used in backpropagration?

I'm learning AI, but this confuses me. The derivative function used in backpropagation is the derivative of activation function or the derivative of loss function? These terms are confusing: ...
2
votes
0answers
158 views

If we use a perceptron with a non-monotonic activation function, can it solve the XOR problem?

I found several papers about how to build a perceptron able to solve the XOR problem. The papers describe a solution where the heaviside step function is replaced by a non-monotonic activation ...
5
votes
5answers
657 views

Why can't the XOR linear inseparability problem be solved with one perceptron like this?

Consider a perceptron where $w_0=1$ and $w_1=1$: Now, suppose that we use the following activation function \begin{align} f(x)= \begin{cases} 1, \text{ if }x =1\\ 0, \text{ otherwise} \end{cases} \...
3
votes
2answers
508 views

Which neural network should I use to approximate a specific function?

We have convolutional neural networks and recurrent neural networks for analysing respectively images and sequential data. How do I determine which neural network architecture is more appropriate to ...
7
votes
4answers
868 views

Is it suitable to find inverse of last layer's activation function and apply it on the target output?

I have a neural network with the following structure: I am expecting specific outputs from the neural network which are the target values for my training. Let's say the target values are 0.8 for the ...
3
votes
1answer
573 views

Is the cube root function suitable as a n activation function?

I am trying to design a neural network on Python. Instead of the sigmoid function which has a limited range, I am thinking of using the cube root function which has the following graph: Is this ...
1
vote
1answer
1k views

Is a linear activation function (in the output layer) equivalent to an identity function?

I have a simple question about the choice of activation function for the output layer in feed-forward neural networks. I have seen several codes where the choice of the activation function for the ...
3
votes
1answer
236 views

Should the input to the negative log likelihood loss function be probabilities?

I am trying to train a supervised model where the output from the model is output of a linear function $WX + b$. Kindly note that I'm not using any softmax or $\log$ softmax on the result of the ...
2
votes
2answers
143 views

Why do non-linear activation functions not require a specific non-linear relation between its inputs and outputs?

A linear activation function (or none at all) should only be used when the relation between input and output is linear. Why doesn't the same rule apply for other activation functions? For example, why ...
0
votes
1answer
614 views

Target values of 0.1 for 0 and 0.9 for 1 for sigmoid

I recently read an article about neural networks saying that, when using sigmoid as activation function, it's advised to use 0.1 as target value instead of 0, and 0.9 instead of 1. This was to avoid "...
7
votes
1answer
86 views

What makes multi-layer neural networks able to perform nonlinear operations?

As I know, a single layer neural network can only do linear operations, but multilayered ones can. Also, I recently learned that finite matrices/tensors, which are used in many neural networks, can ...
10
votes
2answers
246 views

What does it mean for a neuron in a neural network to be activated?

I just stumbled upon the concept of neuron coverage, which is the ratio of activated neurons and total neurons in a neural network. But what does it mean for a neuron to be "activated"? I know what ...
13
votes
1answer
15k views

What are the advantages of ReLU vs Leaky ReLU and Parametric ReLU (if any)?

I think that the advantage of using Leaky ReLU instead of ReLU is that in this way we cannot have vanishing gradient. Parametric ReLU has the same advantage with the only difference that the slope of ...
20
votes
3answers
9k views

How to choose an activation function for the hidden layers?

I choose the activation function for the output layer depending on the output that I need and the properties of the activation function that I know. For example, I choose the sigmoid function when I'm ...
5
votes
1answer
276 views

Which functions can be activation functions?

What are the required characteristics of an activation function (in a neural network)? Which functions can be activation functions? For example, which of the functions below can be used as an ...
8
votes
2answers
5k views

Why do we prefer ReLU over linear activation functions?

The ReLU activation function is defined as follows $$y = \operatorname{max}(0,x)$$ And the linear activation function is defined as follows $$y = x$$ The ReLU nonlinearity just clips the values ...
1
vote
1answer
83 views

Why don't ELUs multiply the linear portion by $\alpha$?

An exponential linear unit (as proposed by Clevert et al.) uses the function: \begin{align} \text{ELU}_\alpha(x) = \begin{cases} \alpha(e^x - 1), &\text{if } x < 0\\ x, \text{if} &\text{if ...
3
votes
2answers
122 views

ANNs with multiple activation outputs

Interested to know if there was any use or interest in activation functions with more than one output value to the next column instead of single firing. I'm interested to know if this would have any ...
10
votes
1answer
2k views

How exactly can ReLUs approximate non-linear and curved functions?

Currently, the most commonly used activation functions are ReLUs. So I answered this question What is the purpose of an activation function in neural networks? and, while writing the answer, it struck ...
30
votes
5answers
17k views

What is the purpose of an activation function in neural networks?

It is said that activation functions in neural networks help introduce non-linearity. What does this mean? What does non-linearity mean in this context? How does the introduction of this non-...
1
vote
2answers
4k views

What is the derivative of the Leaky ReLU activation function?

I am implementing a feed-forward neural network with leaky ReLU activation functions and back-propagation from scratch. Now, I need to compute the partial derivatives, but I don't know what the ...
3
votes
2answers
2k views

Why is no activation function used at the final layer of super-resolution models?

I'm trying to implement some image super-resolution models on medical images. After reading a set of papers, I found that none of the existing models use any activation function for the last layer. ...
2
votes
2answers
223 views

Why do non-linear activation functions that produce values larger than 1 or smaller than 0 work?

Why do non-linear activation functions that produce values larger than 1 or smaller than 0 work? My understanding is that neurons can only produce values between 0 and 1, and that this assumption can ...
2
votes
1answer
824 views

What are the counterparts of non-linearities and dropout in fully convolutional networks?

I am trying to replicate the fully convolutional networks (FCN) concept described here for semantic segmentation. It seems people have successfully trained such models by removing fully connected ...
10
votes
5answers
5k views

Why do activation functions need to be differentiable in the context of neural networks?

Why should an activation function of a neural network be differentiable? Is it strictly necessary or is it just advantageous?
8
votes
3answers
1k views

Are ReLUs incapable of solving certain problems?

Background I've been interested in and reading about neural networks for several years, but I haven't gotten around to testing them out until recently. Both for fun and to increase my understanding, I ...

1 2
3