Derived from: https://github.com/karpathy/nn-zero-to-hero/blob/master/lectures/makemore/makemore_part1_bigrams.ipynb Makemore Purpose: to make more of examples you give it. Ie: names training makemore on names will make unique sounding names this dataset will be used to train a character level language model modelling sequence of characters and able to predict next character in a sequence makemore implements a services of language […]
Blog Posts
Notes for – The spelled-out intro to neural networks and backpropagation: building micrograd
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 […]
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