Lesson 28 of 36
26. Structure of Neural Nets for Deep Learning
Lessons36 lessons
- 1Course Introduction of 18.065 by Professor Strang
- 2An Interview with Gilbert Strang on Teaching Matrix Methods in Data Analysis, Signal Processing,...
- 3Lecture 1: The Column Space of A Contains All Vectors Ax
- 4Lecture 2: Multiplying and Factoring Matrices
- 53. Orthonormal Columns in Q Give Q'Q = I
- 64. Eigenvalues and Eigenvectors
- 75. Positive Definite and Semidefinite Matrices
- 86. Singular Value Decomposition (SVD)
- 97. Eckart-Young: The Closest Rank k Matrix to A
- 10Lecture 8: Norms of Vectors and Matrices
- 119. Four Ways to Solve Least Squares Problems
- 12Lecture 10: Survey of Difficulties with Ax = b
- 13Lecture 11: Minimizing ‖x‖ Subject to Ax = b
- 1412. Computing Eigenvalues and Singular Values
- 15Lecture 13: Randomized Matrix Multiplication
- 1614. Low Rank Changes in A and Its Inverse
- 1715. Matrices A(t) Depending on t, Derivative = dA/dt
- 1816. Derivatives of Inverse and Singular Values
- 19Lecture 17: Rapidly Decreasing Singular Values
- 20Lecture 18: Counting Parameters in SVD, LU, QR, Saddle Points
- 2119. Saddle Points Continued, Maxmin Principle
- 2220. Definitions and Inequalities
- 23Lecture 21: Minimizing a Function Step by Step
- 2422. Gradient Descent: Downhill to a Minimum
- 2523. Accelerating Gradient Descent (Use Momentum)
- 2624. Linear Programming and Two-Person Games
- 2725. Stochastic Gradient Descent
- 2826. Structure of Neural Nets for Deep Learning
- 2927. Backpropagation: Find Partial Derivatives
- 30Lecture 30: Completing a Rank-One Matrix, Circulants!
- 3131. Eigenvectors of Circulant Matrices: Fourier Matrix
- 32Lecture 32: ImageNet is a Convolutional Neural Network (CNN), The Convolution Rule
- 3333. Neural Nets and the Learning Function
- 3434. Distance Matrices, Procrustes Problem
- 3535. Finding Clusters in Graphs
- 36Lecture 36: Alan Edelman and Julia Language
eSIM for studying abroad
A paid placement. It opens Airalo, not a course.