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
21
votes
6answers
11k 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-...
15
votes
3answers
6k views

How to choose an activation function?

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 ...
10
votes
2answers
173 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 ...
10
votes
1answer
9k 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 ...
10
votes
1answer
695 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 (...
9
votes
5answers
3k 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?
7
votes
3answers
2k views

Why is the derivative of the activation functions in neural networks important?

I'm new to NN. I am trying to understand some of its foundations. One question that I have is: why the derivative of an activation function is important (not the function itself), and why it's the ...
7
votes
4answers
549 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 ...
7
votes
2answers
3k 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 ...
6
votes
1answer
262 views

What is the mathematical definition of an activation function?

What is the mathematical definition of an activation function to be used in a neural network? So far I did not find a precise one, summarizing which criterions (e.g. monotonicity, differentiability, ...
6
votes
1answer
301 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 ...
6
votes
1answer
76 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 ...
6
votes
1answer
421 views

What's the advantage of log_softmax over softmax?

Previously I have learned that the softmax as the output layer coupled with the log-likelihood cost function (the same as the ...
5
votes
4answers
1k views

Do neurons of a neural network model a linear relationship?

I'm certain that this is a very naive question, but I am just beginning to look more deeply at neural networks, having only used decision tree approaches in the past. Also, my formal mathematics ...
5
votes
1answer
427 views

Why do ResNets avoid the vanishing gradient problem?

I read that, if we use the sigmoid or hyperbolic tangent activation functions in deep neural networks, we can have some problems with the vanishing of the gradient, and this is visible by the shapes ...
5
votes
2answers
88 views

What should the range of the output layer be when performing classification?

I am working on a MLP neural networks, using supervised learning (2 classes and multi-class classification problems). For the hidden layers, I am using $\tanh$ (which produces an output in the range $[...
4
votes
1answer
114 views

How do intermediate layers of a trained neural network look like?

Suppose I have a deep feed-forward neural network with sigmoid activation $\sigma$ already trained on a dataset $S$. Let's consider a training point $x_i \in S$. I want to analyze the entries of a ...
4
votes
1answer
148 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 ...
3
votes
1answer
342 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 ...
3
votes
1answer
358 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 ...
3
votes
2answers
110 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 ...
3
votes
2answers
148 views

Is PReLU superfluous with respect to ReLU?

Why do people use the $PReLU$ activation? $PReLU[x] = ReLU[x] + ReLU[p*x]$ with the parameter $p$ typically being a small negative number. If a fully connected layer is followed by a at least two ...
3
votes
2answers
96 views

What kind of functions can be used as activation functions?

I read that functions are used as activation functions only when they are differentiable. What about the unit step activation function? So, is there any other reason a function can be used as an ...
3
votes
3answers
382 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 ...
3
votes
2answers
74 views

What could be the problem when a neural network with four hidden layers with the sigmoid activation function is not learning?

I have a large set of data points describing mappings of binary vectors to real-valued outputs. I am using TensorFlow, and would like to train a model to predict these relationships. I used four ...
3
votes
1answer
115 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 ...
3
votes
0answers
38 views

Are there any commonly used discontinuous activation functions?

Are there any commonly used activation functions (e.g. that take values in $(0,.5)\cup (.5,1)$)? Preferably for classification? Why? I was looking for commonly used activation functions on Google, ...
2
votes
2answers
211 views

Why is there a sigmoid function in the hidden layer of a neural network? [duplicate]

I got this slide from CMU's lecture notes. The $x_i$s on the right are inputs and the $w_i$s are weights that get multiplied together then summed up at each hidden layer node. So I'm assuming this is ...
2
votes
1answer
93 views

Why not replacing the simple linear functions that neurons compute with more complex functions?

In a neural network, a neuron typically computes a linear function $f(x) = w*x$, where $w$ is the weight and $x$ is the input. Why not replacing the linear function with more complex functions, such ...
2
votes
2answers
82 views

Is ReLU a non-linear activation function?

According to this blog post The purpose of an activation function is to add some kind of non-linear property to the function The sigmoid is typically used as an activation function of a unit of a ...
2
votes
3answers
121 views

Using sigmoid in LSTM network for multi-step forecasting

I'm trying to develop a multistep forecasting model using LSTM Network. The model takes three times steps as input and predicting two time_steps. both input and output columns are normalised using ...
2
votes
1answer
377 views

Do all neurons in a layer have the same activation function?

I'm new to machine learning (so excuse my nomenclature), and not being a python developer, I decided to jump in at the deep (no pun intended) end writing my own framework in C++. In my current design ...
2
votes
1answer
36 views

What would be the implications of mistakenly adding bias after the activation function?

I was looking at the source code for a personal project neural network implementation, and the bias for each node was mistakenly applied after the activation function. The output of each node was ...
2
votes
2answers
89 views

Can multiple activation functions be replaced with a single activation function?

I'm just started to learn deep learning and I have a question about this neural network: I think $h_1$, $h_j$ and $h_n$ are perceptrons. So, if they are perceptrons, all of them will have an ...
2
votes
1answer
65 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 ...
2
votes
1answer
81 views

Why is a softmax used rather than dividing each activation by the sum?

Just wondering why a softmax is typically used in practice on outputs of most neural nets rather than just summing the activations and dividing each activation by the sum. I know it's roughly the same ...
2
votes
1answer
35 views

Why are activation functions independent layers in CNNs rather than part of convolutional layers?

I have been reading up on CNNs. One of the different confusing things has been that people always talk of normalization layers. A common normalization layer is a ReLU layer. But I never encountered an ...
2
votes
1answer
202 views

Regarding the output layer's activation function for continuous action space problems

I'm interested in building a (deep) RL agent for solving a continuous problem (which splits something into portions). In all examples I've seen so far, e.g., solving the continuous lunar lander, ...
2
votes
1answer
748 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 ...
2
votes
1answer
30 views

Is it possible to apply the associative property of the convolution operation when it is followed by a non-linearity?

The associative property of multidimensional discrete convolution says that: $$Y=(x \circledast h_1) \circledast h_2=x\circledast(h_1\circledast h_2)$$ where $h_1$ and $h_2$ are the filters and $x$ is ...
2
votes
0answers
27 views

What work has been done with Poisson-style regression via neural networks with exponential activation function?

The first neural net I wrote was a classifier. After that, I learned that neural nets can be used for regression tasks, even quantile regression. It has become clear to me that the usual games with ...
2
votes
0answers
30 views

Which activation functions should I use for polynomial regression?

I am a beginner in machine learning and neural networks. I have only used neural networks for classification problems. My aim is to modify it so that it can work for polynomial regression as well. In ...
2
votes
0answers
23 views

Single label classification into hierarchical categories using a neural network

I am working on a classification problem into progressive classes. In other words, there is some hierarchy of categories in such a way, that A < B < C, e.g. low, medium, high, very high. What ...
2
votes
1answer
74 views

How to choose the activation function in neuroevolution?

I am developing a NEAT flappy bird game, and it doesn't work, the system stays stupid for 300 generations. I chose tanh() for activation, just because it's included in JS. I can't find a good ...
2
votes
0answers
14 views

Language Learning feedback with AI

Is there a program under development that uses AI technology, like Siri, to "hold hands" so to speak with a language learner and coach them on accent, colloqiual expressions, or to let them guide the ...
2
votes
0answers
121 views

Non-monotonic activation function and XOR problem with perceptron

I already post the question on Stackoverflow : https://stackoverflow.com/questions/53785922/is-the-use-of-a-non-monotonic-activation-function-is-a-correct-and-viable-solut?noredirect=1#...
2
votes
3answers
137 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 ...
1
vote
2answers
65 views

How are non-linear surfaces formed in the training of a neural network?

Desperate trying to understand something for couple of weeks. All those questions are actually one big question.Please help me. Time-codes and screens in my question refer to this great(IMHO) 3d ...
1
vote
1answer
128 views

Is a non-linear activation function needed if we perform max-pooling after the convolution layer?

Is there any need to use a non-linear activation function (ReLU, LeakyReLU, Sigmoid, etc.) if the result of the convolution layer is passed through the sliding window max function, like max-pooling, ...
1
vote
2answers
3k 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 ...