ConceptUniversal Approximation Theorem
Universal Approximation Theorem
A foundational theorem in deep learning theory stating that a feedforward neural network with at least one hidden layer, a sufficient number of neurons, and a nonlinear activation function can approximate any continuous function defined on a compact set to arbitrary precision. The theorem establishes the theoretical upper bound on the expressive capacity of neural networks.
Timeline (last 90 days)
Oct 26
An MLP is formed by stacking fully connected layers and can theoretically approximate continuous functions to arbitrary precision (universal approximation theorem), but training typically relies on large numbers of iterations and careful hyperparameter tuning, and the parameter count grows rapidly with hidden layer width.
Unverified50%