Questions tagged [softmax]

For questions related to the softmax function, which a function that takes as input a vector of K real numbers, and normalizes it into a probability distribution consisting of K probabilities proportional to the exponentials of the input numbers. The softmax is often used as the activation function of the output layer of a neural network.

Filter by
Sorted by
Tagged with
0 votes
1 answer
34 views

Should softmax be in the model or in the loss function?

Suppose I have an image segmentation model with an output of [ 128, 128, 2 ], segmenting an input image into 2 parts. Commonly, loss functions have the sigmoid or ...
0 votes
0 answers
8 views

Exponentiation immediately after log softmax

In an AlphaZero repo's implementation of Othello game, I see: At one line: F.log_softmax here Next line of the control flow: ...
0 votes
1 answer
50 views

Why didn't my convolutional image classifier network learn anything?

So I am trying to make a CNN image classifier that has two classes, good and bad. The aim is to look at photoshoot pictures that can be found on fashion sites and find the "best one". I ...
  • 101
4 votes
1 answer
196 views

Why are policy gradient methods more effective in high-dimensional action spaces?

David Silver argues, in his Reinforcement Learning course, that policy-based reinforcement learning (RL) is more effective than value-based RL in high-dimensional action spaces. He points out that the ...
16 votes
2 answers
2k views

Are softmax outputs of classifiers true probabilities?

BACKGROUND: The softmax function is the most common choice for an activation function for the last dense layer of a multiclass neural network classifier. The outputs of the softmax function have ...
0 votes
0 answers
29 views

Derivation of the sparsemax loss function

While reading this interesting paper about a sparse variant of the reknown softmax activation function, I got stuck at the section about loss derivation. In particular, I'm having issues understanding ...
1 vote
1 answer
97 views

Why are SVMs / Softmax classifiers considered linear while neural networks are non-linear?

My understanding is that neural networks are definitely not linear classifiers, as the point of functions like ReLU is to introduce non-linearity. However, here's where my understanding starts to ...
  • 151
1 vote
1 answer
171 views

Trouble writing the backpropagation algorithm in python through crossentropy and softmax

so I am writing my own neural network library for a class project and I got everything working for a simple 2-class test using the distance (L2) cost function. I wanted to get a similar result using ...
0 votes
1 answer
186 views

Is the case of a big state space, should we use a softmax exploration policy rather than $\epsilon$-greedy for Q-Learning?

In Reinforcement Learning, epsilon-greedy policies are the most used exploration policies, but in case there is a big state space with impossible actions, wouldn't it be better to use soft-max ...
  • 33
0 votes
1 answer
188 views

Are there any scale invariant activation functions that outputs probability distribution?

Softmax activation function is used to convert any random vector into a probability distribution. So, it is generally used as an activation function in the last layer of deep neural networks that are ...
  • 3,491
-1 votes
1 answer
128 views

Are any non-injective activation functions used?

All activation functions I know of are injective, which I think makes sense. But are there cases where non-injective activations can be useful?
1 vote
0 answers
81 views

Use soft-max post-training for a ReLU trained network?

For a project, I've trained multiple networks for multiclass classification all ending with a ReLU activation at the output. Now the output logits are not probabilities. Is it valid to get the ...
1 vote
1 answer
720 views

Is it normal that the values of the LogSoftmax function are very large negative numbers? [closed]

I have trained a classification network with PyTorch lightning where my training step looks like below: ...
  • 125
0 votes
2 answers
274 views

Where can I read about the multinoulli distribution?

I encountered the term multinoulli distribution in the following sentence from Chapter 4: Numerical Computation of the deep learning book. The softmax function is often used to predict the ...
  • 3,491
0 votes
1 answer
122 views

Which solutions are there to the problem of having too large activations before the softmax (or sigmoid) layer?

I'm trying to build a neural network (NN) for classification using only N-bit integers for both the activations and weights, then I will train it with some heuristic algorithm, based only on the NN ...
2 votes
1 answer
2k views

Why do we use the softmax instead of no activation function?

Why do we use the softmax activation function on the last layer? Suppose $i$ is the index that has the highest value (in the case when we don't use softmax at all). If we use softmax and take $i$th ...
-1 votes
1 answer
114 views

Exploration for softmax should be binary or continuous softmax?

Maybe it's silly to ask but for random exploration in an RL for choosing discrete action, that in the neural network last layer softmax will be used, what random samples should we provide? binary like ...
0 votes
1 answer
332 views

Why does my neural network to solve the XOR problem always output 0.5?

I'm trying to create a neural network to simulate an XOR gate. Here's my dataset: ...
1 vote
1 answer
2k views

Is it appropriate to use a softmax activation with a categorical crossentropy loss?

I have a binary classification problem where I have 2 classes. A sample is either class 1 or class 2 - For simplicity, lets say they are exclusive from one another so it is definitely one or the other....
1 vote
0 answers
77 views

Understanding loss function gradient in asynchronous advantage actor-critic (A3C) algorithm

This is a question I posted here. I am asking it on this StackExchange branch as well, so that more people who could potentially answer get to see the question. In the A3C algorithm from the original ...
1 vote
1 answer
483 views

How to compute the gradient of the cross-entropy loss function with respect to the parameters with softmax activation function?

I've seen plenty of examples of people doing Sigmoid + MSE backpropagation implementations, yet I do not seem to understand how to implement backpropagation as stated in the title in the case of multi-...
0 votes
1 answer
203 views

Why is the derivative of the softmax layer shaped differently than the derivative of other neurons?

If the derivative is supposed to give the rate of change of a function at that point, then why is the derivative of the softmax layer (a vector) the Jacobian matrix, which has a different shape than ...
1 vote
0 answers
57 views

How am I supposed to code equation 4.57 from the book "Machine Learning: An Algorithmic Perspective"?

Consider the equation 4.57 (p. 108) from section 4.6 of the Book Machine Learning: An Algorithmic Perspective, where the derivative of the softmax function is explained $$\delta_o(\kappa) = (y_\kappa -...
1 vote
1 answer
248 views

Why are there two versions of softmax cross entropy? Which one to use in what situation?

I have seen 2 forms of softmax cross-entropy loss and are confused by the two. Which one is the right one? For example in this Quora answer, there are 2 answers: $L(\mathbf{w})=\frac{1}{N} \sum_{n=1}^...
  • 113
5 votes
2 answers
1k views

What is the advantage of using cross entropy loss & softmax?

I am trying to do the standard MNIST dataset image recognition test with a standard feed forward NN, but my network failed pretty badly. Now I have debugged it quite a lot and found & fixed some ...
  • 425
1 vote
2 answers
74 views

Should I use additional empty category in some categorical problems?

I try to create autonomous car using keyboard data so this is a multi class classification problem. I have keys W,A,S and D. So I have four categories. My model should decide what key should be ...
user avatar
3 votes
1 answer
1k views

Which paper introduced the term "softmax"?

Nowadays, the softmax function is widely used in deep learning and, specifically, classification with neural networks. However, the origins of this term and function are almost never mentioned ...
  • 37k
1 vote
0 answers
43 views

Isn't it true that using max over a softmax will be much slower because there is not a smooth gradient?

Isn't it true that using max over a softmax will be much slower because there is not a smooth gradient? Max basically zeros out the gradients of all the non-maximum values. Especially at the beginning ...
  • 568
0 votes
1 answer
943 views

Is the self-attention matrix softmax output (layer 1) symmetric?

Let's assume that we embedded a vector of length 49 into a matrix using 512-d embeddings. If we then multiply the matrix by its transposed version, we receive a matrix of 49 by 49, which is symmetric. ...
  • 111
1 vote
1 answer
64 views

What do the authors of this paper mean by the bias term in this picture of a neural network implementation?

I am reading a paper implementing a deep deterministic policy gradient algorithm for portfolio management. My question is about a specific neural network implementation they depict in this picture (...
  • 131
5 votes
2 answers
1k views

Why does TensorFlow docs discourage using softmax as activation for the last layer?

The beginner colab example for tensorflow states: Note: It is possible to bake this tf.nn.softmax in as the activation function for the last layer of the network....
  • 153
1 vote
1 answer
373 views

Is this neural network with a softmax in the output layer suitable for multi-label classification?

I have data with about 100 numerical features and a multi-labelling that encodes ownership of a certain product (i.e. my labels are of the form $[x_i, i=1, \dots, n]$, where $n$ is the number of ...