Lecture 21: Minimizing a Function Step by Step

Автор: MIT OpenCourseWare

Загружено: 2019-05-16

Просмотров: 41653

Описание:

MIT 18.065 Matrix Methods in Data Analysis, Signal Processing, and Machine Learning, Spring 2018
Instructor: Gilbert Strang
View the complete course: https://ocw.mit.edu/18-065S18
YouTube Playlist: • MIT 18.065 Matrix Methods in Data Analysis...

In this lecture, Professor Strang discusses optimization, the fundamental algorithm that goes into deep learning. Later in the lecture he reviews the structure of convolutional neural networks (CNN) used in analyzing visual imagery.

License: Creative Commons BY-NC-SA
More information at https://ocw.mit.edu/terms
More courses at https://ocw.mit.edu

Lecture 21: Minimizing a Function Step by Step

Доступные форматы для скачивания:

Скачать видео mp4

Информация по загрузке:

Скачать аудио mp3

Похожие видео

22. Gradient Descent: Downhill to a Minimum

22. Gradient Descent: Downhill to a Minimum

9. Four Ways to Solve Least Squares Problems

9. Four Ways to Solve Least Squares Problems

23. Accelerating Gradient Descent (Use Momentum)

23. Accelerating Gradient Descent (Use Momentum)

MIT 6.S191: Convolutional Neural Networks

MIT 6.S191: Convolutional Neural Networks

MIT 18.065 Matrix Methods in Data Analysis, Signal Processing, and Machine Learning, Spring 2018

MIT 18.065 Matrix Methods in Data Analysis, Signal Processing, and Machine Learning, Spring 2018

A Vision of Linear Algebra

A Vision of Linear Algebra

12. Computing Eigenvalues and Singular Values

12. Computing Eigenvalues and Singular Values

Lecture 8: Norms of Vectors and Matrices

Lecture 8: Norms of Vectors and Matrices

David Emil Reich, Professor of Genetics, Harvard Medical School

David Emil Reich, Professor of Genetics, Harvard Medical School

Математики открывают странную новую бесконечность

Математики открывают странную новую бесконечность

25. Stochastic Gradient Descent

25. Stochastic Gradient Descent

MIT 6.S191: Reinforcement Learning

MIT 6.S191: Reinforcement Learning

5. Positive Definite and Semidefinite Matrices

5. Positive Definite and Semidefinite Matrices

2025 MIT Integration Bee - Semifinals

2025 MIT Integration Bee - Semifinals

2025 MIT Integration Bee - Finals

2025 MIT Integration Bee - Finals

Lecture 11: Minimizing ‖x‖ Subject to Ax = b

Lecture 11: Minimizing ‖x‖ Subject to Ax = b

OpenAI goes NUCLEAR (CODE RED)

OpenAI goes NUCLEAR (CODE RED)

KOSZMAR LEWEGO, NAJGORSZY KARNY W KARIERZE? ZDARZA SIĘ NAJLEPSZYM! BARCA I TAK LEPSZA OD ATLETICO

KOSZMAR LEWEGO, NAJGORSZY KARNY W KARIERZE? ZDARZA SIĘ NAJLEPSZYM! BARCA I TAK LEPSZA OD ATLETICO

24. Linear Programming and Two-Person Games

24. Linear Programming and Two-Person Games

21. Eigenvalues and Eigenvectors

21. Eigenvalues and Eigenvectors