Universal Approximation Theorem (Cybenko, 1989):

A single hidden layer network with sufficient neurons can approximate any continuous function to arbitrary accuracy.

\[ F(x) = \sum_{i=1}^{N} w_i \sigma(v_i x + b_i) + w_0 \]

Mathematical statement: For any continuous \(f: [0,1] \to \mathbb{R}\) and \(\epsilon > 0\), there exists \(N\) and parameters such that \(|F(x) - f(x)| < \epsilon\) for all \(x \in [0,1]\).

Key questions:

  1. How many neurons \(N\) do we need?
  2. Is this practical?
  3. Can we verify this experimentally?
 
©  |   Cornell University    |   Center for Advanced Computing    |   Copyright Statement    |   Access Statement
CVW material development is supported by NSF OAC awards 1854828, 2321040, 2323116 (UT Austin) and 2005506 (Indiana University)