Questions tagged [activation-function]

Activation function is a non-linear transformation, usually applied in neural networks to the output of the linear or convolutional layer. Common activation functions: sigmoid, tanh, ReLU, etc.

34 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
4
votes
1answer
554 views

Is it wrong to use Glorot Initialization with ReLu Activation?

I'm reading that keras' default initialization is glorot_uniform. However, all of the tutorials I see are using relu ...
3
votes
0answers
74 views

Why the sigmoid activation function results in sub-optimal gradient descent?

I need some help understanding the second shortcoming of the sigmoid activation function as described in this video from Stanford. She says that because the output of sigmoid is always positive, that ...
3
votes
0answers
96 views

How does one derive the modified tanh activation proposed by LeCun?

In "Efficient Backprop" (http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf), LeCun and others propose a modified tanh activation function of the form: $$ f(x) = 1.7159 * tanh(\frac{2}{3}*x) $$ ...
3
votes
2answers
718 views

Why activation function is not needed during the runtime of an Word2Vec model

In Word2Vec trainable model, there are two different weight matrix. The matrix $W$ from input-to-hidden layer and the matrix $W'$ from hidden-to-output layer. Referring to this article, I understand ...
2
votes
0answers
51 views

Obtaining correctly gradient in neural network of output with respect to input. Is relu a bad option as the activation function?

My neural network is made only by two hidden fully connected units. I've obtained very good results using relu as the activation function, and only good results using softplus. My main purpose is to ...
2
votes
0answers
82 views

Cross error loss function cause division by zero error

How to calculate cross entropy when actual output is 0? Would not it give indf brcause of log(0) and the cross entropy for binary classification is given by: -(ylog(actual_output)+(1-y)*(1-...
2
votes
4answers
71 views

Few activation functions handling various problems - neural networks

How can a few activation functions in neural networks handle so many different problems? I know some basics theory behind ANN, but I can't get what functions like the sigmoid function etc. have in ...
1
vote
1answer
12 views

Scaling the activation function

It is obvious that I have to scale the output data if the range of values is between say [-10;10] and the activation function of the output layer takes values in the interval [-1;1]. But I could also ...
1
vote
0answers
60 views

What is the reason behind Keras choice of default (recurrent) activation functions in LSTM networks

Activation function between LSTM layers In the above link, the answer to the question whether activation function are required for LSTM layers was answered as follows: as an LSTM unit already consists ...
1
vote
0answers
17 views

Sharing parameters of an activation across layers of a neural network

Keras now provides advanced parametric activation layers like Leaky-ReLU PReLU. Each time I add this layer to a sequential model, an additional trainable parameter is added to graph. How can I make ...
1
vote
0answers
13 views

Using Iterative Hard/Soft Thresholding in autoencoder with non linear activation

Can someone please give an intuitive explanation of the difference between the Iterative Hard Thresholding VS Iterative Soft thresholding algorithm? And if we can use these algorithms in an ...
1
vote
0answers
13 views

Wich activation function for DQL

After many research, I still can't find a neat answer about this question: When I found the loss of my state-action pair. I'm only backpropagating that loss true the network and setting all other ...
1
vote
1answer
37 views

Should output data scaling correspond to the activation function's output?

I am building an LSTM with keras which have an activation parameter in the layer. I have read that scaling on the output data ...
1
vote
0answers
116 views

Generalized softmax derivative for implementation with any loss function

I am currently taking some deep learning and neural network (NN) courses, and in addition to performing the course work, am implementing my own "toolkit" of NN techniques to better my understanding of ...
1
vote
0answers
25 views

Which activation function of the output layer and which loss function are advised to be used for bounded regression?

I want my (deep) neural network to produce an output from a certain range, in my case between 0 and 255. I have scaled the labels from [0..255] to [0..1]. For the neural network, I have tried a ...
1
vote
0answers
13 views

How does one use activation function with greater than [-1;1] range for binary classification?

In Efficient Backprop (http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf), Lecun and others propose to use activation function that don't reach target values on their asypmptotes. They explain (§ 4....
1
vote
0answers
33 views

Should I scale/normalize the data before training a feedforward neural network using only lagged values?

So I am trying to forecast the price of a certain commodity that is quite volatile. Now I wanted to train a regression feedforward neural network to predict the price of next week. Just to be clear, ...
1
vote
1answer
116 views

Relationship between Sigmoid and Gaussing Distribution

I was reading this article where I came across the following statement in the context of "Why do we use sigmoid activation function in Neural Nets?": The assumption of a dependent variable to follow ...
1
vote
0answers
2k views

What are best activation and regularization method for LSTM?

In Keras there are: ...
1
vote
0answers
42 views

Regression with -1,1 target range - Should we use a tanh activation in the last 1 unit dense layer?

Say in a regression problem the target range to be between [0,1] or [-1,1], and say the last layer of the network is as ...
1
vote
0answers
1k views

Understanding of threshold value in a neural network

Consider the hypothetical neural network here $o_1$ is the output of neuron 1. $o_2$ is the output of neuron 2. $w_1$ is the weight of connection between 1 and 3. $w_2$ is the weight of connection ...
1
vote
0answers
38 views

How to Implement Biological Neuron Activations in Artificial Neural Networks

In artificial neural networks, activation functions are used for neurons, i.e. the sigmoid activation: Which can be implemented in code as (in Python): ...
1
vote
0answers
114 views

Why isn't Maxout used in the state of the art models?

I have just read the paper from Ian Goodfellow et al. titled "Maxout Networks". It seems that the Maxout activation should be quite powerful, as it can approximate any convex function, i.e. Relu, ...
0
votes
0answers
29 views

Avoid saturation in activation function (sigmoid)

Background It is said Sigmoid/Tanh are not to use because of the saturation issue. Question The saturation occurs when the input to Sigmoid/Tanh is a large value. Will normalizing the input between -...
0
votes
0answers
25 views

Neural network output is 0 for test data (using RELU for activation)

Maybe this is a naive question, but I have a NN that uses relu for all layers. In train data there is no problem, but in test (or validation) the outputs are all 0. ...
0
votes
0answers
15 views

Conv1D relu: negative values or additional sequence?

If I have sequences that can have negative values with occasional spikes in both positive and negative directions I'd like to preserve, what is the best practice to handle those sequences: should I ...
0
votes
0answers
17 views

proper activation function at output and loss function to optimize for OCR?

I am trying to make a CNN model on IAM handwritten words data(which has images of words handwritten by multiple people and targets are text in the images). So, I can encode words to numbers(A=0, B=1 ...
0
votes
2answers
37 views

What is the meaning of colors in activation maps?

I am trying to understand how the neural network works. I plotted the intermediate layer activations and I got the following image. I used the matplotlib library and selected ...
0
votes
1answer
29 views

Example of convex activation function

For a particular task, I need a convex activation function with the following properties: f''(x) > 0 0 <= f(x) <= 1 f(x) is monotonic f(x) is not "exploding" i.e. avoiding functions such as ...
0
votes
0answers
19 views

If input data to CNN is not normalised, how should I initialise the weights?

I've read that He normalisation is preferred for Relu activated CNN's. However, understanding how Relu's work by linearly activating positive inputs while zero or negative inputs are zero'd (with no ...
0
votes
0answers
125 views

Writing a piecewise linear function as a sum of ReLU functions

Suppose I have a piecewise linear function $f(x) = \sum^n_{i=1}a_i\phi_i(x)$, where $\{\phi_i\}_{i=1}^n$ is a finite dimension space of dimension $n-1$, in particular I am interested in the functions ...
0
votes
0answers
64 views

Is it reasonable to use the output of the sigmoid function as the win rate prediction?

I'm working on a project which is predicting the win rate of one team or one person. (could be any kind of sports like baseball, basketball or e-sport games) The data I have is more like a ...
0
votes
3answers
444 views

What are the best activation functions for Binary text classification in neural networks?

I know that there are many activation functions like Relu, sigmoid, tanh ..etc, I just want to know the best one for my case - Binary text classification. I have heard that Relu is best for Binary ...
0
votes
0answers
19 views

What are contexts where a perceptron model could be defined?

per this post, a perceptron could use the logit function as the activation function. per wiki In the context of neural networks, a perceptron is an artificial neuron using the Heaviside step ...