Artificial Neural Network Example: Visualizing a Simple Perceptron

① This GeoGebra example demonstrates a simple artificial neural network with an input layer, a hidden layer, and an output layer, showing how weighted sums and activation functions produce outputs. ② Core mathematical concepts include linear functions, piecewise functions (e.g., step or sigmoid), logistic regression, weights and biases, and the basics of backpropagation. ③ Construction uses GeoGebra commands such as Segment, Point, and Textfield; objects include weights (w_1 to w_8), biases (b_1, b_2), net input (net_{h1}), and output (out_{h1}), allowing interactive adjustment of parameters to observe changes in the network's output. ④ Suitable for high school to university-level mathematics or computer science courses, this example serves as an intuitive teaching tool for understanding linear algebra, function composition, and parameter optimization in neural networks, and as an introductory AI visualization.