Sign inSign in
ConceptAI & ML

Universal function approximator

Neural networks are universal function approximators, meaning if you can differentiate it, a neural network can approximate it.
as John M. Aiken defines itUT AustinThe wording closest to all 3 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.

Neural networks3Differentiation1Function space1Non-linear activation functions1

Lecturers

3

Each in their own terms, from the easiest level.

  • Jeremy Bernstein

    MIT · Undergraduate

    The property of neural networks that allows them to express any class of functions.
    • 1:17Approximation Theory
  • Pieter Abbeel

    UC Berkeley · Undergraduate

    A two-layer neural network with a sufficient number of neurons and non-linear activations can approximate any continuous mapping from input to output up to arbitrary precision.
    • 4:43Machine Learning: Neural Networks and Decision Trees

Connections

6

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

Concepts3

Lectures3

3 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.