Question

How can I derive the back propagation formula in a more elegant way?

score 3k · Answer 1 · 2026-03-25 17:39:37

3k

Views

How can I derive the back propagation formula in a more elegant way?

Published on 25 Mar 2026 - 17:39

score 391 · Answer 2 · 2026-03-25 08:12:43

391

Views

Reference Request: Neural Networks as Mathematical Models

Published on 25 Mar 2026 - 8:12

score 66 · Answer 3 · 2014-12-28 10:02:28

66

Views

How to understand ' Let $\mathcal{H}$ be a Hilbert space of functions $f$ : $ \mathcal{X} \rightarrow R$, denoted on a non-empty set $\mathcal{X}$.'

Published on 28 Dec 2014 - 10:02

score 86 · Answer 4 · 2014-12-28 14:32:27

86

Views

How to prove $\Phi_w(x)=\cos (w^T x+b)$ is outside the RKHS associated with the Gaussian kernel function$K(x,y)=\exp(-\frac{||x-y||^2}{2\sigma})$?

Published on 28 Dec 2014 - 14:32

score 114 · Answer 5 · 2014-12-29 02:45:28

114

Views

How to prove this specific kernel is not in RKHS?

Published on 29 Dec 2014 - 2:45

score 242 · Answer 6 · 2014-12-29 03:12:12

242

Views

Difference among convergence almost surely, in probability, and in distribution. And advantages.

Published on 29 Dec 2014 - 3:12

score 24 · Answer 7 · 2026-03-28 20:59:16

24

Views

unique children of a point in a boolean lattice

Published on 28 Mar 2026 - 20:59

score 96 · Answer 8 · 2015-01-02 23:03:18

96

Views

Understanding a step while calculating the gradient of the log-likelihood of Restricted Boltzmann Machines

Published on 02 Jan 2015 - 23:03

score 41 · Answer 9 · 2026-03-28 23:57:39

41

Views

Proof that gradient descent algorithm escapes saddle points exponentially

Published on 28 Mar 2026 - 23:57

score 745 · Answer 10 · 2026-03-28 08:37:02

745

Views

Solving constrained minimisation problem using unconstrained optimization of the generalized Lagrangian

Published on 28 Mar 2026 - 8:37

score 140 · Answer 11 · 2026-03-25 16:06:35

140

Views

proof: maximum likelihood and least square is pseudo-inverse

Published on 25 Mar 2026 - 16:06

score 53 · Answer 12 · 2026-03-26 22:15:24

53

Views

Derivative of Cross Entropy of Finite Discrete Random Variables

Published on 26 Mar 2026 - 22:15

score 3.2k · Answer 13 · 2019-10-09 14:58:05

3.2k

Views

How to Show that AdaBoost Weighted Error is Exactly 1/2

Published on 09 Oct 2019 - 14:58

score 2.5k · Answer 14 · 2019-10-11 19:47:36

2.5k

Views

What is the motivation for using cross-entropy to compare two probability vectors?

Published on 11 Oct 2019 - 19:47

score 83 · Answer 15 · 2019-10-12 08:01:00

83

Views

Matrix calculus for RNN equations

Published on 12 Oct 2019 - 8:01

List Question

How can I derive the back propagation formula in a more elegant way?

Reference Request: Neural Networks as Mathematical Models

How to understand ' Let $\mathcal{H}$ be a Hilbert space of functions $f$ : $ \mathcal{X} \rightarrow R$, denoted on a non-empty set $\mathcal{X}$.'

How to prove $\Phi_w(x)=\cos (w^T x+b)$ is outside the RKHS associated with the Gaussian kernel function$K(x,y)=\exp(-\frac{||x-y||^2}{2\sigma})$?

How to prove this specific kernel is not in RKHS?

Difference among convergence almost surely, in probability, and in distribution. And advantages.

unique children of a point in a boolean lattice

Understanding a step while calculating the gradient of the log-likelihood of Restricted Boltzmann Machines

Proof that gradient descent algorithm escapes saddle points exponentially

Solving constrained minimisation problem using unconstrained optimization of the generalized Lagrangian

proof: maximum likelihood and least square is pseudo-inverse

Derivative of Cross Entropy of Finite Discrete Random Variables

How to Show that AdaBoost Weighted Error is Exactly 1/2

What is the motivation for using cross-entropy to compare two probability vectors?

Matrix calculus for RNN equations

Trending Questions

Popular # Hahtags

Popular Questions