策略引擎>> perceptron-single-layer>> 返回
项目作者： josgard94

项目描述 ：
Python implementation of the simple perceptron or also known as a single-layer neural network, is a binary classification algorithm by Frank Rosenblatt based on the neural model of Warren McCulloch and Walter Pitts developed in 1943.
高级语言： Python
项目地址: git://github.com/josgard94/perceptron-single-layer.git
创建时间： 2020-07-13T02:54:29Z
项目社区：https://github.com/josgard94/perceptron-single-layer
开源协议：
下载


🇪🇸 Leer en Español

🧠 Single-Layer Perceptron

Welcome to this classic machine learning project! This repository contains a Python implementation of a single-layer perceptron, also known as a simple neural network, proposed by Frank Rosenblatt in 1958 and inspired by the neural model of McCulloch and Pitts (1943).

📘 Description

The perceptron simulates the basic behavior of a brain neuron:

  • It receives inputs 🧾 (x)
  • Each input is multiplied by a weight 📊 (w)
  • An activation function is applied (z = w·x + b)
  • If the result exceeds a certain threshold (θ), the neuron is activated 🔥

This algorithm is a binary linear classifier, used for supervised learning.

⚙️ Features

  • 🐍 Implemented in Python
  • 🎯 Performs binary classification
  • 📈 Step-by-step training with weight updates
  • 🧪 Includes visualizations of training results

📸 Screenshots

🔹 Decision region example 1

Decision Boundary

🔹 Decision region example 2

Learning Process

🚀 How to Run

Make sure you have Python 3 and the required dependencies installed:

  1. pip install -r requirements.txt

Then run the main script:

  1. python main.py

📚 References

  • Rosenblatt, F. (1958). The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain.

  • McCulloch, W. S., & Pitts, W. (1943). A Logical Calculus of the Ideas Immanent in Nervous Activity.

⭐ Give it a Star

If you found this project helpful or interesting, don’t forget to leave a ⭐!