Skip to main content
Share Your Experience: Take the 2024 Developer Survey
2 votes

One Softmax or two separate logistic regressions for the task of classifying pictures as a/b and c/d

It is possible to have an output for every combination of independent classes. As another poster has noted this scales poorly. It is also possible to have a network which diverges into two sets of ...
foreverska's user avatar
  • 1,263
2 votes
Accepted

One Softmax or two separate logistic regressions for the task of classifying pictures as a/b and c/d

Softmax gives you a probability distribution, thus its output are positive and sum to 1... if you want "outdoor" AND "daytime", you want a $1$ on the "outdoor" neuron and ...
Alberto's user avatar
  • 2,153
1 vote

How to evaluate the KL divergence between two distributions that may require sampling?

The distribution being conditional or not does not change the notion of KL divergence. Indeed, given $p(x) \sim N(\mu_1, \sigma_1^2)$ and $q(x) \sim N(\mu_2, \sigma_2^2)$, the KL can be estimated in ...
Alberto's user avatar
  • 2,153
1 vote
Accepted

Does a random forest classifier always get 100% accuracy on its own training data?

No, random forest is not guaranteed to get 100% accuracy on the test data. But it also doesn’t mean it’s overfit because relatively high scores on test data are common with random forests. The trees ...
foreverska's user avatar
  • 1,263
1 vote
Accepted

Book(s) recomendation for Probability Theory Foundations

This right here is the money shot. https://ocw.mit.edu/courses/18-05-introduction-to-probability-and-statistics-spring-2022/pages/classes-reading-and-in-class-materials/ That's essentially what you're ...
Joseph's user avatar
  • 51
1 vote

How does Training and Validating work with Graph CNNs

There are two main settings of doing training/validation/testing in graphs: Inductive Setting: You datasets consists of multiple graph (e.g. molecules) and you simply split the graphs into training/...
Chillston's user avatar
  • 1,748

Only top scored, non community-wiki answers of a minimum length are eligible