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
2answers
68 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 ...
3
votes
1answer
106 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 ...
1
vote
1answer
80 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 ...
1
vote
0answers
22 views

If the output of a model is a ridge function, what should the activation functions at all the nodes be?

I have the following assignment. I can't understand the b part of this question in my assignment. I have completed the 1st part and understand the maths behind it, but the 2nd part has me stumped. I ...
13
votes
2answers
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 ...
19
votes
6answers
10k 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-...
10
votes
1answer
8k 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 ...
1
vote
0answers
13 views

Poisson regression via neural network

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
28 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 ...
1
vote
1answer
26 views

Are activation functions applied to feature maps?

If I have a convolutional neural network, and I convolve my input tensor with a kernel, the output is a feature map. Is an activation function then applied to this feature map? If its an image that ...
1
vote
0answers
19 views

Can SqueezeNet be used for regression?

I want a model that outputs the pixel coordinates of the tip of my forefinger, and whether it's touching something or not. Those would be 3 output neurons: 2 for the X-Y coordinates and 1, with a ...
2
votes
1answer
72 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 ...
1
vote
2answers
59 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 ...
2
votes
0answers
22 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
62 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 ...
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, ...
1
vote
0answers
28 views

Are PreLU and Leaky ReLU better than ReLU in the case of noisy labels?

Let's assume I want to build a semantic segmentation algorithm, based on Multires-UNET. My GT-masks are messy and generated by a GAN, but they are getting better and better over time. The goal is ...
1
vote
1answer
176 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 ...
2
votes
3answers
117 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 ...
1
vote
0answers
25 views

Which activation functions can lead to the vanishing gradient problem?

From this video tutorial Vanishing Gradient Tutorial, the sigmoid function and the hyperbolic tangent can produce the vanishing gradient problem. What other activation functions can lead to the ...
6
votes
1answer
75 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 ...
1
vote
0answers
25 views

What are the pros and cons of the common activation functions?

I have heard that sigmoid activation functions should not be used on neural networks with many hidden layers as the gradients tend to vanish in deep networks. When should each of the common ...
1
vote
1answer
23 views

What is the equation of the separation line for this neuron with identity activation?

I have a single neuron with 2 inputs, and identity activation, where f is activation function and u is output: $u = f(w_1x_1 + ...
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 ...
1
vote
1answer
94 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, ...
5
votes
1answer
253 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 ...
6
votes
1answer
357 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 ...
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 ...
1
vote
0answers
24 views

What activation functions are better for what problems?

I’ve been reading about neural network architectures. In certain cases, people say that the sigmoid "more accurately reflects real-life" and, in other cases, functions like hard limits reflect "the ...
6
votes
1answer
260 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, ...
2
votes
1answer
76 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
292 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 ...
3
votes
2answers
71 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 ...
2
votes
2answers
192 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 ...
1
vote
1answer
97 views

When should I use a linear activation instead of ReLU?

I have read this post: How to choose an activation function?. There is enough literature about activation functions, but when should I use a linear activation instead of ReLU? What does the author ...
5
votes
4answers
994 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 ...
10
votes
2answers
167 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 ...
2
votes
2answers
76 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
732 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 ...
0
votes
1answer
68 views

Network doesn't converge with ReLU or Leaky ReLU, but works well with sigmoid/tanh

I have these training data to separate, the classes are rather randomly scattered: My first attempt was using tf.nn.relu activation function, but output was stuck ...
6
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 ...
5
votes
2answers
87 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 $[...
3
votes
2answers
131 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 ...
2
votes
1answer
29 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 ...
4
votes
1answer
103 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 ...
3
votes
3answers
371 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
1answer
75 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 ...
2
votes
1answer
190 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, ...
4
votes
1answer
145 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 ...