How can you determine the class probabilities from the logits i.e. the results from output layer? 1 pointUsing sigmoid functionUsing ReLu functionBy normalizing them within 0 and 1Using softmax function

You can determine the class probabilities from the logits (the results from the output layer) by using the softmax function.

Here's a step-by-step guide:

1. Compute the logits: The logits are the raw scores output by the last layer of your neural network. They are unnormalized, meaning they can take any real value, not just between 0 and 1.

2. Apply the softmax function: The softmax function is a function that takes a vector of K real numbers and normalizes it into a probability distribution consisting of K probabilities. That is, prior to applying softmax, some vector components could be negative, or greater than one; and might not sum to 1; but after applying softmax, each component will be in the interval (0,1), and the components will add up to 1, so that they can be interpreted as probabilities.

The softmax function is given by the formula: Softmax(x)_i = exp(x_i) / Σ_j exp(x_j)

3. Interpret the output: The output of the softmax function is a vector that represents the probability distributions of a list of potential outcomes. It's a way of rescaling the logits so that they can be interpreted as probabilities.

Note: The sigmoid function is used in binary classification problems (where an instance can belong to one of two classes). The ReLU function is an activation function used within the neural network, not for normalizing the output. Normalizing within 0 and 1 is a type of scaling, not a way to get probabilities from logits.