Sign inSign in
ConceptAI & ML

Softmax

A function that converts a vector of logits into a probability distribution by exponentiating each value and normalizing by the sum.
as Chris Ré defines itStanford UniversityThe wording closest to all 8 definitions
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Opens up

Concepts that name this one as a prerequisite.

Lecturers

8

Each in their own terms, from the easiest level.

  • Sara Beery

    MIT · Undergraduate

    A function that takes a vector of real numbers and normalizes it into a probability distribution.
    • 48:52Architectures: Memory
  • Andrej Karpathy

    Undergraduate

    An activation function that exponentiates and normalizes logits to output a valid probability distribution.
    • 1:27:28Spelled-Out Intro to Language Modeling: Building makemore (Bigram & Cross-Entropy)
  • Christopher Manning

    Stanford University · Undergraduate

    A probability formula that exponentiates and normalizes vector scores.
    • 54:49Natural Language Processing with Deep Learning: Introduction & Word Vectors
  • Patrick Winston

    MIT · Undergraduate

    A function that takes an output vector and normalizes the values into probabilities across multiple classes.
    • 35:00Deep Neural Networks: MIT Artificial Intelligence
  • Pieter Abbeel

    UC Berkeley · Undergraduate

    A mathematical function that converts a vector of raw scores (activations) into a probability distribution that sums to one.
    • 1:03:07Machine Learning: Perceptrons and Logistic Regression
  • Phillip Isola

    MIT · Undergraduate

    A function that maps an arbitrary real-valued vector to a probability distribution over classes, residing on a simplex.
    • 12:06Representation Learning: Reconstruction-Based
  • Trenton Bricken

    Stanford University · Graduate

    A function that normalizes a vector of values into a probability distribution, making larger values more prominent.
    • 10:52Neuroscience-Inspired Artificial Intelligence

Lectures that assume it

15

The first 12 are shown.

Connections

33

The lectures that define it or assume it, and the concepts next to it.

Concepts10

Show 4 more

Lectures23

Show 17 more

8 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.