Summary of above: Backpropagation is just a recursive application of chain rule backward through the graph storing the computed derivative as a gradient (grad) variable within each node. Gotcha! We must be careful that when adding multiple of the same term we correctly derive wrt all terms instead of just a single term! Ie: b […]
Blog Posts
December 7th, 2022
How ML (machine learning) Works
If you are here, you are probably wasting your time. Below is a summary of notes I have taken for working through this: I defer you to that resource because Andrej is my mentor wrt ML. If you want to know my specific thoughts and things that I have learned from his “Building makemore” class, […]
Machine Learning Ideas
Create a neural net that weighs price difference % $TSLA for the past 1, 2, 3, 4, 5, 10, 15, 30, 60, 90 and 180 days. Starting with a binomial, you can create a data set that looks at the % change between yesterday and today. Just like makemore will make name predictions, the predictions […]
Tesla’s Businesses
Tesla’s Current Businesses Home charging stations New Car Sales Model S (2012) Model 3 (2017) Model X (2014) Model Y (2019) Used Car Sales Repairs parts and labour Insurance (2019) Fueling Stations – Superchargers (2012) Solar panels (2016) Home Battery Storage(2015) Grid Storage(2019) Virtual Power Plant(2022) Tesla’s Future Businesses Robo-taxi Neural Net Training Robots
Plan to Rob Elon Musk
Of the 100,000+ employees hired by Tesla, if you take the worst employee per thousand employees, that is still 100 employees. These employees could range from parasites trying to incorporate dependencies on Tesla for special interests, to malicious mischief makers, liars, thieves, or saboteurs. But single employees can only do so much damage before suspicions […]