47
votes
Accepted
Why is ReLU used as an activation function?
In mathematics (linear algebra) a function is considered linear whenever a function$f: A \rightarrow B$ if for every $x$ and $y$ in the domain $A$ has the following property: $f(x) + f(y) = f(x+y)$. ...
39
votes
Accepted
What is GELU activation?
GELU function
We can expand the cumulative distribution of $\mathcal{N}(0, 1)$, i.e. $\Phi(x)$, as follows:
$$\text{GELU}(x):=x{\Bbb P}(X \le x)=x\Phi(x)=0.5x\left(1+\text{erf}\left(\frac{x}{\sqrt{2}}...
27
votes
Accepted
Why ReLU is better than the other activation functions
The biggest advantage of ReLu is indeed non-saturation of its gradient, which greatly accelerates the convergence of stochastic gradient descent compared to the sigmoid / tanh functions (paper by ...
22
votes
Accepted
How to use LeakyRelu as activation function in sequence DNN in keras?When it perfoms better than Relu?
You can use the LeakyRelu layer, as in the python class, instead of just specifying the string name like in your example. It works similarly to a normal layer.
Import the LeakyReLU and instantiate a ...
17
votes
Accepted
Difference of Activation Functions in Neural Networks in general
A similar question was asked on CV: Comprehensive list of activation functions in neural networks with pros/cons.
I copy below one of the answers:
One such a list, though not much exhaustive:
...
14
votes
How to create custom Activation functions in Keras / TensorFlow?
First you need to define a function using backend functions. As an example, here is how I implemented the swish activation function:
...
13
votes
Why is ReLU used as an activation function?
I understand the advantages of ReLU, which is avoiding dead neurons during backpropagation.
This is not completely true. The neurons are not dead. If you use sigmoid-like activations, after some ...
11
votes
Neural Network not Deep
The term 'deep' in deep learning is not well defined, but is generally meant to apply to networks that have stacked multiple layers on top of each other to create a deep network. It is therefore up ...
10
votes
Accepted
What is the purpose of multiple neurons in a hidden layer?
To explain using the sample neural network you have provided:
Purpose of the multiple inputs: Each input represents a feature of the input dataset.
Purpose of the hidden layer: Each neuron learns a ...
10
votes
Accepted
Why do so many functions used in data science have derivatives of the form f(x)*(1-f(x))?
Sigmoid function is a partial case of softmax, when the number of classes $K=2$. That's why the similarity of their derivatives shouldn't surprise you.
Why do so many functions used in data science ...
10
votes
What is GELU activation?
First note that $$\Phi(x) = \frac12 \mathrm{erfc}\left(-\frac{x}{\sqrt{2}}\right) = \frac12 \left(1 + \mathrm{erf}\left(\frac{x}{\sqrt2}\right)\right)$$ by parity of $\mathrm{erf}$. We need to show ...
9
votes
Accepted
Input normalization for ReLu?
You have to normalize your data to accelerate learning process but based on experience its better to normalize your data in the standard manner, mean zero and standard deviation one. Although mapping ...
9
votes
How does Sigmoid activation work in multi-class classification problems
If your task is a kind of classification that the labels are mutually exclusive, each input just has one label, you have to use Softmax. If the inputs of your ...
9
votes
Can the vanishing gradient problem be solved by multiplying the input of tanh with a coefficient?
You are correct. For $n > 1$, the multiplication of derivatives does not necessarily go to zero, because each derivative could be potentially larger than one (up to $n$).
However, for practical ...
8
votes
Why is activation needed at all in neural network?
Generally the activation is part of the model and gets applied for each neuron, so definitely before the error calculation. What the activation function is depends on what task you are solving and ...
5
votes
Accepted
Activation function vs Squashing function
An activation function
This the name given to a function, which is applied to a neuron that just had a weight update as a result of new information. It can refer to any of the well known activation ...
5
votes
Activation function vs Squashing function
Activation functions like sigmoid function, hyperbolic tangent function, etc. are also called squashing function because they squash the input into a small range like in sigmoid function output is in ...
5
votes
How does Sigmoid activation work in multi-class classification problems
softmax() will give you the probability distribution which means all output will sum to 1. While, sigmoid() will make sure the output value of neuron is between 0 to 1.
In case of digit ...
5
votes
What does it mean for an activation function to be "saturated/non-saturated"?
Please see this answer.
An activation function is considered non-satured if
$$
\lim_{z \rightarrow \infty} f(z) = \infty
$$
A saturated activation function has a compact range such as $[-1,1]$ for $...
4
votes
Accepted
Why are sigmoid/tanh activation function still used for deep NN when we have ReLU?
In certain network structures having symmetric activation layers has advantages (certain autoencoders for example)
In certain scenarios having an activation with mean 0 is important (so tanh makes ...
4
votes
Accepted
Why is an activation function notated as "g"?
The addition of the activation layer creates a composition of two functions.
"A general function, to be defined for a particular context, is usually denoted by a single letter, most often the lower-...
4
votes
Is classifier able to say there's no-such-case?
Taking your questions one after the other:
Assume that I have a classifier which can classify left hand / right
hand well. I am curious whether it can decide whether there's a hand
in the image?...
4
votes
Why is ReLU used as an activation function?
The main reason to use an Activation Function in NN is to introduce Non-Linearity. And ReLU does a great job in introducing the same.
Three reasons I choose ReLU as an Activation Function
First it'...
4
votes
Alternatives to linear activation function in regression tasks to limit the output
Don't use that activation function shown in the question. It doesn't do what you think it does. Instead:
If you want the output to be in the range $[-1,1]$, you can use a sigmoid or tanh activation ...
4
votes
How to use LeakyRelu as activation function in sequence DNN in keras?When it perfoms better than Relu?
Just to add another solution.
You can also write something like
import tensorflow as tf
keras = tf.keras
...
4
votes
Accepted
Can we use ReLU activation function as the output layer's non-linearity?
Yes, you can. Basically, for regression tasks, it is customary to use the linear function as the non-linearity due to the fact that it's differentiable and it does not limit the output. This means you ...
4
votes
How batch normalization layer resolve the vanishing gradient problem?
Batch Normalization (BN) does not prevent the vanishing or exploding gradient problem in a sense that these are impossible. Rather it reduces the probability for these to occur. Accordingly, the ...
3
votes
Accepted
Properly using activation functions of neural network
How is data predicted from activation functions? (considering that it returns constants on weighted input sum).
You should consider the fact that the label of your input data is going to be ...
3
votes
Is classifier able to say there's no-such-case?
Many classifiers do not directly give you L or R. They will give you the option which has a higher decision metric. For Naive Bayes this would be the class with the higher probability between $p(L|x)$ ...
3
votes
Advantages of monotonic activation functions over non-monotonic functions in neural networks?
I don't know of any papers about this topic, but intuitively it makes a lot of sense to use monotonic activation functions. Let's say we have a non-monotonic activation function, maybe a Gaussian ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
activation-function × 150neural-network × 83
deep-learning × 58
machine-learning × 47
keras × 23
classification × 11
tensorflow × 11
regression × 10
python × 9
backpropagation × 9
gradient-descent × 8
cnn × 7
loss-function × 6
lstm × 4
autoencoder × 4
softmax × 4
pytorch × 3
numpy × 3
mathematics × 3
dataset × 2
data-mining × 2
image-classification × 2
convolutional-neural-network × 2
visualization × 2
reinforcement-learning × 2