221
reputation
1
8

Eric Leschinski

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 outcome."

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 predicts outcomes.

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 today is that a budget computer from walmart with $2500 worth of NVidia GPU's (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 outperform the best humans ( and their optimally tuned 1*10^18 signal-processing neurons and 100TB bio-memory) at narrowly defined tasks.

To excel in machine learning: make sure to understand all math themed classes: Algebra, Discrete and continuous mathematics, Probability, Statistics, Set/decision theory, Calculus I through III and get good at reading Math equations and computer code, and having an intuition for what they are doing and why.

The reason machine learning is good for everyone is because it offloads repetitive motion from a human, so they can focus on higher level tasks. The human brain grows like layers laid down on a cake, over the Millennia. Now man machine hybrids are the next step of evolution as Elon Musk number two (in the year 2050-2100) hammers out Gigabit up/down over neural lace behind your ear, over bluetooth to a phablet in your pocket then over 5G to a private desktop supercluster or a Gigaton amazon data center.

The calculation of the slope of a tangent of a point on a curve is the one super secret trick that caused evolution and the environment to give mammals brains. Amplifying this and hybridizing that to biology over an analog-digital set top box, will enable humans to eventually re-engineer ourselves to live in space as easily as the surface of planets. Eventually completing the celestial circuit of why we are here: evolving to create our own ancestor that garbage collects the current universe; plus an infusion of energy, correctly reforged; a reproduction of the physics engine that creates life.

https://mubaris.com/posts/linear-regression

2
answers
1
question
~12k
people reached
  • Member for 4 years, 10 months
  • 3 profile views
  • Last seen Nov 6 '18 at 11:45

Top tags (3)

Score 6
Posts 3
Score 3
Posts 2
Score 3
Posts 2

Top posts (3)

Badges (9)

Gold

Silver

1

Rarest

Bronze

8

Rarest