EPISODE · Jun 8, 2018 · 24 MIN
Modeling Evolution with Tensorflow.js
from Siraj Raval
Neuroevolution is a technique that uses evolutionary algorithms to generate artificial neural networks (ANN), parameters, topology and rules. We can think of it as an optimization strategy, similar to gradient descent, that can in some cases be faster to converge and give better results. We're going to simulate evolution by creating neural network creatures in javascript and having them evolve over time to try and walk across the screen. I'll discuss the steps that our algorithm will take, then code out the neural network class at the end of the video. Code for this video: https://github.com/llSourcell/Modeling_Evolution_with_TensorflowJS Please Subscribe! And like. And comment. That's what keeps me going. Want more education? Connect with me here: Twitter: https://twitter.com/sirajraval Facebook: https://www.facebook.com/sirajology instagram: https://www.instagram.com/sirajraval More learning resources: https://medium.com/tensorflow/a-gentle-introduction-to-tensorflow-js-dba2e5257702 http://thecodingtrain.com/CodingChallenges/100.2-neuroevolution-flappy-bird.html https://becominghuman.ai/designing-ai-solving-snake-with-evolution-f3dd6a9da867 https://www.cs.ucf.edu/~kstanley/neat.html https://blog.coast.ai/lets-evolve-a-neural-network-with-a-genetic-algorithm-code-included-8809bece164 https://eng.uber.com/deep-neuroevolution/ Join us in the Wizards Slack channel: http://wizards.herokuapp.com/ Sign up for the next course at The School of AI: https://www.theschool.ai And please support me on Patreon: https://www.patreon.com/user?u=3191693
What this episode covers
Neuroevolution is a technique that uses evolutionary algorithms to generate artificial neural networks (ANN), parameters, topology and rules. We can think of it as an optimization strategy, similar to gradient descent, that can in some cases be faster to converge and give better results. We're going to simulate evolution by creating neural network creatures in javascript and having them evolve over time to try and walk across the screen. I'll discuss the steps that our algorithm will take, then code out the neural network class at the end of the video. Code for this video: https://github.com/llSourcell/Modeling_Evolution_with_TensorflowJS Please Subscribe! And like. And comment. That's what keeps me going. Want more education? Connect with me here: Twitter: https://twitter.com/sirajraval Facebook: https://www.facebook.com/sirajology instagram: https://www.instagram.com/sirajraval More learning resources: https://medium.com/tensorflow/a-gentle-introduction-to-tensorflow-js-dba2e5257702 http://thecodingtrain.com/CodingChallenges/100.2-neuroevolution-flappy-bird.html https://becominghuman.ai/designing-ai-solving-snake-with-evolution-f3dd6a9da867 https://www.cs.ucf.edu/~kstanley/neat.html https://blog.coast.ai/lets-evolve-a-neural-network-with-a-genetic-algorithm-code-included-8809bece164 https://eng.uber.com/deep-neuroevolution/ Join us in the Wizards Slack channel: http://wizards.herokuapp.com/ Sign up for the next course at The School of AI: https://www.theschool.ai And please support me on Patreon: https://www.patreon.com/user?u=3191693
NOW PLAYING
Modeling Evolution with Tensorflow.js
No transcript for this episode yet