<aside> 💡 아래 포스트는 네이버 Boostcamp AI-Tech 과정 중 고려대학교 인공지능학과 최성준 교수님의 DL Basic 수업 및 자료를 바탕으로 재구성한 것입니다.

</aside>

Introduction

Deep Learning

Neural Networks

Neuron vs. Perceptron (source: https://inteligenciafutura.mx/english-version-blog/blog-06-english-version)

Neuron vs. Perceptron (source: https://inteligenciafutura.mx/english-version-blog/blog-06-english-version)

Artificial neural networks (ANNs), usually simply called neural networks (NNs), are computing systems inspired by the biological neural networks that constitute animal brains.[1]

Mathematical Definition

Neural networks are funciton approximators that stack affine transformations followed by nonlinear transformations.

Universal Approximator Theorem

"Multilayer Feedforward Networks are Universal Approximators"[2]

Sums of the form

$$ \sum_{j=1}^{N} \alpha_j \sigma(y_j^\top x + \theta_j) $$

where $y_j \in \mathbb{R}^n$ and $\alpha_j, \theta_j \in \mathbb{R}$, are dense in the space of continuous functions on the unit cube if $\sigma$ is any continuous sigmoidal function.