A computer program is said to learn from experience with respect to a class of tasks and a performance measure
P, if its performance at tasks as measured by
P improves with experience beyond a baseline of accuracy defined by: "Guessing the most frequently occurring correct answer."
3Blue1Brown, how trained neural networks simulate human abilities: https://www.youtube.com/watch?v=aircAruvnKk
Machine Learning is mostly just a matter of getting good at programming. The annoying part of machine learning is data transformation from a given arrangement to a needed arrangement. The reason
y=mx+b from high school Algebra and the derivative from Calculus I through III is the beginning of machine learning is because the slope of a tangent to a point on a curve is an extractor of information gain that separates a superior brain from an inferior one at the speed of light. The algorithm that the universe uses to create life is wait for it, "the partial derivative from Calculus 3 of multiple dimensions with respect to one, over a surface hyperplane. https://www.youtube.com/watch?v=EkZGBdY0vlg
CGP Grey, how the genetic algorithm can simulate human abilities: https://www.youtube.com/watch?v=R9OHn5ZF4Uo
Machine learning principles have been well-known since the 1960's. The difference now is a budget computer an NVidia GPU (or a cheap EC2 instance) gives you more 32-bit floating point operations per second than ten million dollars worth of computer in 1990. So now computers are starting to isolate computer models that can outperform the models that humans make for their own brains at narrowly defined tasks.
To excel at machine learning: understand all computer sicence and math themed classes:
Discrete and continuous mathematics,
Calculus I through III and get good at intuition for transforming math to code and back.
The reason machine learning is good for humanity is because it offloads unpleasant repetitive motion from a humans, so they can focus on higher level tasks that might be more fun. The human brain grows like a cake over the generations with the inch behind your forehead the newest. Now man machine hybrids are the next step of evolution as Musk number two (2050-2100) hammers out Gigabit/sec up/down over neural lace behind your ear, bluetooth to a phablet, then over wireless tower to a private desktop supercluster or a Gigaton amazon data center.
Amplifying this cybernetic isolation of new brains, and hybridizing that in computers to humans through an analog-to-digital converter tuned to the person, will enable humans to amplify evolution to make space a habitable zone for naked humans. Eventually completing the celestial circuit of why are we here? We're made to evolve to create our own ancestor that garbage collects the universe; with a siiip of rockstar, correctly reforged; a reproduction of the Physics engine that creates life, for the 6th time.
Member for 2 years, 6 months
10 profile views
Last seen Apr 5 '19 at 18:01