Polynomial Regression — An Alternative For Neural Networks?

A discussion of polynomials and neural networks, which theoretically are both able to approximate continuous functions infinitely closely.

Polynomial Regression - An Alternative For Neural Networks? | Towards Data Science Data Science Polynomial Regression – An Alternative For Neural Networks? A discussion of polynomials and neural networks, which theoretically are both able to approximate continuous functions infinitely closely. Wouter van Heeswijk, PhD Feb 7, 2022 14 min read Share Example of polynomial regression performed on a data set, using three different degrees of polynomials. Theoretically, polynomials can achieve infinitely close fits. [image from WikiMedia by Shobha ] To start: this is more a discussion piece th

saved by

• Grady Kenix

related reading

• Toy Models of Superpositiontransformer-circuits.pub
• Zoom In: An Introduction to Circuitsdistill.pub
• Neural Networks, Manifolds, and Topology -- colah's blogcolah.github.io
• A Recipe for Training Neural Networkskarpathy.github.io
• Neural networks and deep learningneuralnetworksanddeeplearning.com
• Universal approximation theorem - Wikipediaen.wikipedia.org
• Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
• Neural Networks, Types, and Functional Programming -- colah's blogcolah.github.io
• A Recipe for Training Neural Networkskarpathy.github.io
• [2503.02113] Deep Learning is Not So Mysterious or Differentarxiv.org
• arxiv.org/pdf/1805.08522arxiv.org
• Neural network training makes beautiful fractals | Jascha’s blogsohl-dickstein.github.io