# 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.

10 questions
Filter by
Sorted by
Tagged with
36 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 -...
160 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}^...
93 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 ...
30 views

### Why do we use a Softmax regression? [closed]

Could someone explain to me why, with examples?
53 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 ...
85 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 ...
33 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 ...
69 views

### Transformers - 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 it transposed version we receive a matrix of 49 by 49. Which is symmetric. ...