Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Genetic Algorithms And Artificial NeuralNets in Vanilla JS
Rating: 4.4 out of 5(62 ratings)
4,045 students

Genetic Algorithms And Artificial NeuralNets in Vanilla JS

How to combine Artificial Neural Nets and Genetics Algorithms to build powerful AI using only Javascript(No Libraries)
Created byAlexsandro Souza
Last updated 1/2025
English

What you'll learn

  • How Evolutionary algorithms works
  • Artificial Neural Networks
  • How to train a model to play different games
  • Alternative way to train Artificial Neural networks

Course content

1 section • 8 lectures • 52m total length

  • Introduction3:13
  • Source code
  • What is Neuroevolution?18:50
  • Artificial Neural Networks9:07
  • Neuralevolution training3:38

    Demonstrates neural evolution training for game agents, using sensor inputs and fitness-based selection across generations to rapidly learn tasks like car navigation and flappy bird play.

  • NeuroEvolution library7:34
  • Visualise the network behaviour during the training9:02

    Visualize the training behavior of a neural network to add explainability, showing weights, biases, and activation across layers, from inputs to outputs, during training with evolutionary algorithms.

  • Conclusion1:01

Requirements

  • Basic Javascript knowledge

Description

In this short course, we will build a Neuroevolution model from scratch using only JavaScript (no libraries) that will learn to play various games.


Neuroevolution is a powerful approach to machine learning and artificial intelligence that uses evolutionary algorithms to evolve neural networks.

Most neural networks use gradient descent rather than neuroevolution. However, around 2017 researchers at Uber stated they had found that simple structural neuroevolution algorithms were competitive with sophisticated modern industry-standard gradient-descent deep learning algorithms.

Deep Neuroevolution: Genetic Algorithms are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning

This course introduces students to the principles of neuroevolution and the techniques used to design and implement neuroevolution algorithms.

The course covers the following topics:

  1. Introduction to neuroevolution: basic principles and applications

  2. Evolutionary algorithms: genetic algorithms, genetic programming, and evolutionary strategies

  3. Neural networks: types, architectures, and training techniques

  4. Neuroevolution algorithms: evolutionary algorithms applied to neural networks

  5. Applications of neuroevolution: games, and optimization problems

  6. Advanced topics: multi-objective neuroevolution, neuroevolution of recurrent neural networks, and deep neuroevolution.

In this project, we have applied GeneticEvolution to multiple games such as self-driving cars, smart caps and flappy bird.


This course is a follow-up to my other course about Artificial Neural Networks from scratch, where I show how to create an ANN from scratch without libraries. In that project, the learning process is done using backpropagation(gradient descent), this project uses a different approach. We will use Evolutionary Algorithm.


By following this course until the end,  students will have a solid understanding of the principles of neuroevolution and the ability to design and implement Neuroevolution algorithms for a variety of applications.


Who this course is for:

  • Web developers curious about deep learning and AI

Report abuse