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 accuracy of: "Guessing the most frequently occurring correct answer."
The money shot is creating a computer model that can perform a market demanded task at an acceptable speed, accuracy and hostile-user tolerance, that it becomes a source automatic income such that the cost of a computer, electricity, software and internet + maintenance is less than the human employment alternative. The money arbitrage opportunity and money fountain comes from the fact that people always want to pay less for an adequate service.
3Blue1Brown, how trained neural networks simulate human abilities: https://www.youtube.com/watch?v=aircAruvnKk
Machine Learning is just computer programming. The annoying part 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 (drumroll please) "The partial derivative from Calculus of a 3D function with respect to one dimension, deriving a 2D hyperplane of max separation and using that to config the neuron".
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 with a $1100 NVidia 2080TI GPU, (or cheap EC2 instance) gives you more 32-bit floating point operations (10-20 TFLOPS) than ten million dollars worth of computer in 1990. So now a middle class amateur can isolate a model that outperform the models that even the best humans make for themselves at narrowly defined tasks.
To fast track machine learning: pay attention in all computer science and math themed classes:
Discrete and continuous mathematics(set logic/theory),
Calculus 1-3(derivatives) and get good at intuition for transforming math to computer code and back.
The reason machine learning is good for everyone is because it replaces necessary unpleasant repetitive motion from humans, so they can focus on higher level tasks that might be more fun. The human brain grows like a cake over the centuries 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 4G wireless tower to a private desktop ML-supercluster or amazon data center.
Member for 5 years, 3 months
3 profile views
Last seen Nov 6 '18 at 11:45