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.

Filter by
Sorted by
Tagged with
0
votes
0answers
12 views

Saturation of exponential linear units (ELU)

The ELU activation function saturates to $-a$ for large negative inputs. \begin{align} f(x) = \left\{ \begin{array}{rcl} a(\text{exp}(x) - 1) & \mbox{for } x \leq 0 \\ x & \...
0
votes
2answers
29 views

Is there any point in having layers in a neural network for regression problems?

In my textbook I read that an MLP and linear activation functions for the hidden layers can be reduced to a simple input-output system, i.e. no hidden layers. This makes sense to me. Later on I read ...
0
votes
0answers
9 views

Feature importance by removing all other features?

For neural network feature importance, can I zero-out all features except one in order to gauge that feature's importance? I know shuffling a feature is one approach. For example, leaving in the 4th ...
0
votes
2answers
29 views

Activation and Loss Function not chosen correctly when use Neural Network

I have three classes for my text dataset before. These are my classes: 0 = Cat 1 = Not Both 2 = Dog Then I use this code: ...
2
votes
0answers
14 views

Derive backpropagation for PreLU

I want to derive the back propagation functions for the Parametric Relu activation function which is defined as follows: $$ h_a(x) = \text{max}(ax, x) $$ I want to derive $ \frac{\partial L}{\partial ...
1
vote
0answers
21 views

What meaning does exp function have?

Is there any problem that solution(or algorithm) would be exp function? Let's say f(x)=2^x. It's an answer of a problem when you would like to know how many pieces would be made when you fold a paper ...
1
vote
0answers
21 views

The case of (1,478) dim and parameters of neural network to find out

colleagues, actually I am kind'a new to NN, but hard trying.. I have data: Index: 40073 entries (excluded from training, UID) Columns: 484 entries dtypes: bool(468), float64(2), int64(13), object(1) I ...
7
votes
2answers
179 views

Why deep learning models still use RELU instead of SELU, as their activation function?

I am a trying to understand the SELU activation function and I was wondering why deep learning practitioners keep using RELU, with all its issues, instead of SELU, which enables a neural network to ...
1
vote
1answer
435 views

Difference between ReLU, ELU and Leaky ReLU. Their pros and cons majorly

I am unable to understand when to use ReLU, ELU and Leaky ReLU. How do they compare to other activation functions(like the sigmoid and the tanh) and their pros and cons.
1
vote
0answers
36 views

Word embedding autoencoder

I'm trying to train a word embedding autoencoder, but it either doesn't train, or trains but doesn't make predictions. I know I'm doing something wrong, so any help is greatly appreciated. Here is my ...
0
votes
0answers
13 views

Bounded regression problem: sigmoid, hard sigmoid or…?

I have been training a neural network for a bounded regression and I am still in doubt for which activation function to use on the output layer. At first, I was convinced that a sigmoid would be the ...
1
vote
1answer
56 views

Activation Function

I am very new to machine learning and made an experiment myself. I have a few questions: Can I use $Y = sin(x)$ or $Y = 2x$ as an activation function for a neural network? Is it necessary to increase ...
1
vote
2answers
41 views

How can the ReLU function lead to convergence?

The gradient descent algorithm is based on the fact that the gradient decreases as we move towards the optimum point. However, in the activations by the ReLU ...
1
vote
0answers
14 views

If the input to the autoencoder is normalized, do we need to use sigmoid on the last layer?

According to: https://stackoverflow.com/questions/65307833/why-is-the-decoder-in-an-autoencoder-uses-a-sigmoid-on-the-last-layer The last layer activation function contains sigmoid in order to the ...
1
vote
1answer
40 views

Is there comprehensive list of activation functions and their applications for a Neural Network?

I am aware of common activation functions like sigmoid, tanh,ReLu, Leaky ReLu. Even heard about a function called Swish. Now is there any detailed information on other activations functions and some ...
1
vote
1answer
50 views

Can this dataset be separated linearly?

Is this dataset linearly separable? If not, can it be converted into one by applying some function as it seems to follow the same pattern? Also, which classification algorithms could be used to fit ...
2
votes
1answer
942 views

How batch normalization layer resolve the vanishing gradient problem?

According to this article: https://towardsdatascience.com/the-vanishing-gradient-problem-69bf08b15484 The vanishing gradient problem occurs when using the sigmoid ...
0
votes
1answer
52 views

Why the gradient of a ReLU for X>0 is 1?

Gradient is derivative of several variables. I can't understand why is the gradient of a ReLU for X>0 is 1 ? and 0 for x < 0 ? I tried to search for proof and examples but didn't found any good ...
1
vote
1answer
36 views

Training set Distribution and Activation function/Loss function correlation

How should the probability distribution of the training set influence the choice of the activation function / loss function? For instance if I have a Multinoulli distribution, which activation ...
2
votes
1answer
30 views

Do Activation Functions map to Higher Dimensions?:

I just started learning tensorflow and I have a question regarding activation functions used in neural networks, I watched a 3b1b video a while ago and it seems it squished the value into an interval ...
0
votes
1answer
46 views

Numerically stable hyperbolic tangent

The hyperbolic tangent is commonly used as an activation function: $$ tanh(x) = \frac{e^x - e^{-x}}{e^x + e^{-x}} $$ Although, it is unclear how this function is implemented to be numerically stable ...
0
votes
1answer
46 views

Applying activation on part of the layer in Keras

Context I am trying to implement the YOLO algorithm in Keras. What I have so far is the following network: ...
0
votes
1answer
41 views

Is it possible to implement a vectorized version of a Maxout activation function?

I want to implement an efficient and vectorized Maxout activation function using python numpy. Here is the paper in which "Maxout Network" was introduced (by Goodfellow et al). For example, ...
0
votes
1answer
44 views

Input and output layer activation functions of neurons in Orange

What are the activation functions of the neurons in the input and output layer of a neural network model from the Orange machine learning application?
0
votes
1answer
18 views

Can there be in-active neuron in output layer

I am new to deep learning, and was studying about it. I know that input from input layer is multiplied with weights and then added with bias. And output of this is passed to a activation function of a ...
1
vote
0answers
18 views

Does the number of hidden layers affect the activation function?

Suppose there's a network with N hidden layers. There are 2 cases: The network is deep The network is shallow I've been wondering how ...
0
votes
0answers
14 views

Guidelines to efficiently train neural networks which have polynomial activations

I am interesting in studying low footprint NN by replacing the activation functions with low-degree polynomial approximations. Doing this, I am fine with slight reduction in accuracy if I the training ...
0
votes
0answers
31 views

tanh function values are either 1 or -1, how to interpret that distribution

I have a question regarding the tanh function. I trained an NN (with tanh activation functions in hidden layers) on a multiclass dataset and visualised the tanh values of the complete samples from the ...
0
votes
0answers
21 views

Sigmoid vs Softmax with cross entropy

For a binary classifier, Is there any difference in Sigmoid activation function vs Softmax with cross entropy ? In this answer how-to-maximize-recall it is stated that if we use softmax with cross ...
0
votes
0answers
22 views

Sigmoid activation function for scaled continuous data

I've been working on a NLP project that attempt to output a single numeric value. The natural form of the data is integers between 0 and 27, with 27 being an absolute maximum, and values above 27 ...
1
vote
1answer
22 views

Are non-relu activations better for small/ dense datasets?

Building on the questions below, the only conclusion I could draw from the answers was that ReLu is less computationally expensive and better at sparsity. Why is ...
0
votes
1answer
14 views

Does sigmoid facilitate modeling non-linear decision boundaries or does this come from high-dimensional data?

I'm writing up a neural network using sigmoid as the activation function. According to one lecture, sigmoid simply squashes numbers onto the (0,1) interval. To model non-linear decision boundaries, ...
0
votes
0answers
9 views

How to determine activation functions for neural network

I am trying to plan a neural network for regression predictions. The final activation layer should be a linear function, but for hidden layers, do the activation functions need to also be all linear ...
1
vote
0answers
13 views

Can we talk about vanishing activations?

When updating the weights of a deep neural network using backpropagation, to update the weights of a given hidden layer, we use both the partial derivatives of the objective function with respect to ...
0
votes
1answer
55 views

How to deal with ternary Output neurons in the Output classification layer of a simple feedforward Neural Net?

I was looking into the multi-label classification on the output layer of a Neural Network. I have 5 Output Neurons where each Neuron can be 1, 0, or -1. independent of other Neurons. So for example an ...
1
vote
1answer
110 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
1answer
263 views

Problem with convergence of ReLu in MLP

I created neural network from scratch in python using only numpy and I'm playing with different activation functions. What I observed is quite weird and I would love to understand why this happens. ...
1
vote
1answer
130 views

Dying leaky ReLU

I am trying to train a deep neural network but I am having dying ReLU problem. I am using leaky Relu but still have the same problem. Isn't leaky relu supposed to not have such problems?
1
vote
1answer
81 views

Is it possible to get an ROC curve using Relu activation?

Based on my understanding, given that Relu doesn't provide probabilities unlike Softmax, it's not possible to plot an ROC curve. However, is there some way to convert the output from a Relu to ...
1
vote
0answers
304 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 ...
3
votes
1answer
170 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 ...
2
votes
1answer
576 views

As RELU is not differentiable when it touches the x-axis, doesn't it effect training?

When I read about activation functions , I read that the reason we don't use step function is because, it is non differentiable which leads to problem in gradient descent. I am a beginner in deep ...
2
votes
1answer
106 views

Output landscape of ReLU, Swish and Mish

I found the following figure in the original Mish paper (https://arxiv.org/abs/1908.08681). I understand that this figure describes how the loss is being changed, if the change is smooth or not. But ...
1
vote
0answers
22 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
26 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 ...
0
votes
0answers
34 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 ...
1
vote
1answer
306 views

How does Pytorch deal with non-differentiable activation functions during backprop?

I've read many posts on how Pytorch deal with non-differentiability in the network due to non-differentiable (or almost everywhere differentiable - doesn't make it that much better) activation ...
1
vote
0answers
15 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 ...
3
votes
2answers
691 views

What does the descision boundary of a relu look like?

A single non activated neuron is just a linear combination of its inputs. Thresholding this neuron's output as-is against 0 would create a hyperplane binary separator, whose parameters can be learned....
7
votes
2answers
1k views

Why leaky relu is not so common in real practice?

As leaky relu does not lead any value to 0, so training always continues. And I can't think of any disadvantages it have. Yet Leaky relu is less popular than Relu in real practice. Can someone tell ...