Why Neural Networks can learn (almost) anything
A video about neural networks, how they work, and why they're useful.
My twitter: / max_romana
SOURCES
Neural network playground: https://playground.tensorflow.org/
Universal Function Approximation:
Proof: / hornik.pdf
Covering ReLUs: https://proceedings.neurips.cc/paper/...
Covering discontinuous functions: https://arxiv.org/pdf/2012.03016.pdf
Turing Completeness:
Networks of infinite size are turing complete: Neural Computability I & II (behind a paywall unfourtunately, but is cited in following paper)
RNNs are turing complete: https://binds.cs.umass.edu/papers/199...
Transformers are turing complete: https://arxiv.org/abs/2103.05247
More on backpropagation:
• Backpropagation, step-by-step | DL3
More on the mandelbrot set:
• The Mandelbrot Set - Numberphile
Additional Sources:
Neat explanation of universal function approximation proof: • The Universal Approximation Theorem f...
Where I got the hard coded parameters: https://towardsdatascience.com/can-ne...
Reviewers:
Andrew Carr / andrew_n_carr
Connor Christopherson
TIMESTAMPS
(0:00) Intro
(0:27) Functions
(2:31) Neurons
(4:25) Activation Functions
(6:36) NNs can learn anything
(8:31) NNs can't learn anything
(9:35) ...but they can learn a lot
MUSIC
• It Was Here
Watch video Why Neural Networks can learn (almost) anything online without registration, duration hours minute second in high quality. This video was added by user Emergent Garden 12 March 2022, don't forget to share it with your friends and acquaintances, it has been viewed on our site 1,283,774 once and liked it 50 thousand people.