Lecture 2 | The Universal Approximation Theorem

Показать описание

Carnegie Mellon University
Course: 11-785, Intro to Deep Learning
Offering: Fall 2019

Contents:
• Neural Networks as Universal Approximators

Carnegie Mellon University Deep Learning

Рекомендации по теме

Комментарии

a great explanation...Thank you so much

cedricmanouan

Couldn't help but think of 3B1B videos on hamming codes watching this.

ian-haggerty

Very nice lecture. I feel I understand better why neural networks work.

adhoc

Such a cool explanation. Can anyone (in particular any student from this course) provide a link to a mathematical explanation behind the content from 35:00 till 45:00. Usually lecturers do provide references to such material. Please do not share the reference papers already listed in this video.

Learner_

A great and very clear lecture. Thank you.

samanrazavi

At 15:25, isn't the total input coming L-N if first L inputs are 0 and last N-L inputs 1?

bhargavram

can any one explain the inequality in 41:30

and the equation in 42:00

thanks

husamalsayed

This guy is confusing. No good explanations. I have doubts about the two circle one hidden layer solution. He nees an OP operation as a third layer, otherwise also other regions outside of the two cicles will be above the threshold.

smftrsddvjiou

Is this a undergrad level course or grad level course?

ITPCD

Lecture 2 | The Universal Approximation Theorem

Lecture 2 | The Universal Approximation Theorem

(Old) Lecture 2 | The Universal Approximation Theorem

Lecture 2: Neural Nets as Universal Approximators

Introduction to Deep Learning Lecture 2

F18 Lecture 2: The Neural Net as a Universal Approximator

Lecture 2: What is Meant by Computation?

Lecture 2: Image Classification

Lecture 2: Neural Networks - What can a network represent

Universal Café Day: 3 MIND-BLOWING AI Art Creations Using YouTube Audio Library

Lecture 2 Water, Acids, Bases, and Buffers

Peter Zoller: Introduction to quantum optics - Lecture 2

Lecture 2: Cantor's Theory of Cardinality (Size)

11-785, Spring 22 Lecture 2: Neural Nets as Universal Approximators

Lecture 2: Morphology, Part 1

Deep Learning - Lecture 3.4 (Deep Neural Networks: Universal Approximation)

Constitution 101 | Lecture 2

Introduction to Radar Systems – Lecture 2 – Radar Equation; Part 1

Leonard Susskind | Lecture 2: Black Holes and the Holographic Principle

Albert Camus, Lecture 2: Repetition & Futility

Special Relativity | Lecture 2

11-785, Fall 22 Lecture 2: Neural Networks: What can a network represent

Noam Chomsky, Fundamental Issues in Linguistics (April 2019 at MIT) - Lecture 2

Aeschylus's Agamemnon. Lecture 2 by Michael Davis

Universal Law of Gravitation - Part 2 | Physics | Don't Memorise