Fun Fun Function | Better training of our neural network - Let's code a neural network in plain JavaScript Part 3 @funfunfunction | Uploaded July 2018 | Updated October 2024, 2 hours ago.
🔗 Support the show by becoming a Patreon
youtube.com/watch?v=trP9q703x0o

🔗 (Patrons only) Official discussion topic for this episode on the Fun Fun Forum:
funfunforum.com/t/lets-code-a-neural-network-in-plain-javascript/5211


🔗Code from the episode
beta.observablehq.com/@mpj/neural-network-from-scratch-part-1

🔗 Playlist for this series
youtube.com/playlist?list=PL0zVEGEvSaeGmPpG8tAaqSmf3k56LPwiF

🔗 Daniel Shiffman video that inspired this video
youtube.com/watch?v=ntKn5TPHHAk

🔗 Intro to ObservableHQ
youtube.com/watch?v=MmRmxzrr4lk

🔗 But what is a neural network by 3blue1brown
youtube.com/watch?v=aircAruvnKk

🔗 mpj on Twitter
twitter.com/mpjme

🔗 Help translate the show to your language
youtube.com/timedtext_cs_panel?tab=2&c=UCO1cgjhGzsSYb1rsB4bFe4Q

Let’s make a neural network, completely from scratch, in JavaScript! No machine learning libraries, no prior knowledge of machine learning, statistics, advanced math and no diving into neuroscience, just the plain code. In this episode, we look at how to improve the training of our neural network using a learning rate.