Formula: Artificial Neuron (Q156): Difference between revisions
Jump to navigation
Jump to search
Added content item: Formula: Artificial Neuron |
Changed claim: LaTeX source (P4): $\begin{aligned}\text{Let } \mathbf{x} = (x_1,\dots,x_n)^\top \in \mathbb{R}^n \text{ be the input vector} \\\text{Let } \mathbf{w} = (w_1,\dots,w_n)^\top \in \mathbb{R}^n \text{ be the weight vector} \\\text{Let } b \in \mathbb{R} \text{ be the scalar bias} \\\text{The affine pre‑activation is } z = \mathbf{w}^\top \mathbf{x} + b = \sum_{i=1}^n w_i x_i + b \\\text{Choose a non‑linear activation } \sigma: \mathbb{R} \to \mathbb{R} \\\text{The arti... |
||
| (2 intermediate revisions by the same user not shown) | |||
| Property / instance of | |||
| Property / instance of: mathematical expression / rank | |||
Normal rank | |||
| Property / LaTeX source | |||
$\begin{aligned}\text{Let } \mathbf{x} = (x_1,\dots,x_n)^\top \in \mathbb{R}^n \text{ be the input vector} \\\text{Let } \mathbf{w} = (w_1,\dots,w_n)^\top \in \mathbb{R}^n \text{ be the weight vector} \\\text{Let } b \in \mathbb{R} \text{ be the scalar bias} \\\text{The affine pre‑activation is } z = \mathbf{w}^\top \mathbf{x} + b = \sum_{i=1}^n w_i x_i + b \\\text{Choose a non‑linear activation } \sigma: \mathbb{R} \to \mathbb{R} \\\text{The artificial neuron output is } y = \sigma(z) \in \mathbb{R} \\\text{Typical activations: } \sigma(z) = \mathbf{1}_{z \ge 0} \text{ (step)}, \quad \sigma(z) = (1+e^{-z})^{-1} \text{ (sigmoid)}, \quad \sigma(z) = \max(0,z) \text{ (ReLU)}\end{aligned}$ | |||
| Property / LaTeX source: $\begin{aligned}\text{Let } \mathbf{x} = (x_1,\dots,x_n)^\top \in \mathbb{R}^n \text{ be the input vector} \\\text{Let } \mathbf{w} = (w_1,\dots,w_n)^\top \in \mathbb{R}^n \text{ be the weight vector} \\\text{Let } b \in \mathbb{R} \text{ be the scalar bias} \\\text{The affine pre‑activation is } z = \mathbf{w}^\top \mathbf{x} + b = \sum_{i=1}^n w_i x_i + b \\\text{Choose a non‑linear activation } \sigma: \mathbb{R} \to \mathbb{R} \\\text{The artificial neuron output is } y = \sigma(z) \in \mathbb{R} \\\text{Typical activations: } \sigma(z) = \mathbf{1}_{z \ge 0} \text{ (step)}, \quad \sigma(z) = (1+e^{-z})^{-1} \text{ (sigmoid)}, \quad \sigma(z) = \max(0,z) \text{ (ReLU)}\end{aligned}$ / rank | |||
Normal rank | |||
| Property / source | |||
| Property / source: Rong Martin-Siebler ZHOU / rank | |||
Normal rank | |||
| Property / describes | |||
| Property / describes: programming language / rank | |||
Normal rank | |||
Latest revision as of 19:10, 17 August 2026
No description defined
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Formula: Artificial Neuron |
No description defined |
Statements
$\begin{aligned}\text{Let } \mathbf{x} = (x_1,\dots,x_n)^\top \in \mathbb{R}^n \text{ be the input vector} \\\text{Let } \mathbf{w} = (w_1,\dots,w_n)^\top \in \mathbb{R}^n \text{ be the weight vector} \\\text{Let } b \in \mathbb{R} \text{ be the scalar bias} \\\text{The affine pre‑activation is } z = \mathbf{w}^\top \mathbf{x} + b = \sum_{i=1}^n w_i x_i + b \\\text{Choose a non‑linear activation } \sigma: \mathbb{R} \to \mathbb{R} \\\text{The artificial neuron output is } y = \sigma(z) \in \mathbb{R} \\\text{Typical activations: } \sigma(z) = \mathbf{1}_{z \ge 0} \text{ (step)}, \quad \sigma(z) = (1+e^{-z})^{-1} \text{ (sigmoid)}, \quad \sigma(z) = \max(0,z) \text{ (ReLU)}\end{aligned}$
0 references