Foundations of Deep Learning and AI

A rigorous, encyclopedic reference on the mathematical foundations of Deep Learning and Artificial Intelligence, organized as interlinked concept pages with precise definitions, formulations, and limitations.


Definition

A neural network is a parametric function
\(f_\theta : \mathbb{R}^n \to \mathbb{R}^m\) defined as a composition of affine maps and nonlinear activation functions.


Mathematical Formulation

A feedforward neural network with $L$ layers is given by: \(f(x) = W_L \sigma(W_{L-1} \sigma( \cdots \sigma(W_1 x + b_1)) + b_{L-1}) + b_L\)


Key Properties


Limitations