An interactive exploration of the mathematical foundations of artificial neurons, powered by Streamlit. This project visualizes how weights, inputs, and biases interact to produce a neuron's output.
This project aims to demystify the core mechanics of a single perceptron. By providing a hands-on interface, it demonstrates:
- Linear Aggregation: How multiple input signals are weighted and combined.
- The Role of Bias: How the bias term shifts the activation function independent of inputs.
-
Mathematical Logic: The direct relationship between the linear equation
$y = \sum (w_i \cdot x_i) + b$ and the neuron's behavior.
Access the deployed project here: Streamlit
The application guides you through three levels of complexity:
-
Single Input: Basic signal transmission (
$y = w \cdot x$ ). - Dual Input: Weighted summation of two distinct sources.
- Triple Input with Bias: A complete linear model incorporating a bias term for offset control.