4. In linear discrimination, gradient descent is used to find the minimum of the error function. With error function defined as the cross entropy E(w, wo X) == − Σ[rt log y² + (1 - rt) log(1 - y¹)] and yt = tanh(w²xt + wo), derive the update for w, where j ‡ 0. Note: Given y = tanh(a), the derivative by = 1 - y². да

Algebra & Trigonometry with Analytic Geometry
13th Edition
ISBN:9781133382119
Author:Swokowski
Publisher:Swokowski
Chapter7: Analytic Trigonometry
Section7.6: The Inverse Trigonometric Functions
Problem 93E
icon
Related questions
Question

please explain all details thanks .

4.
In linear discrimination, gradient descent is used to find the minimum of the error
function. With error function defined as the cross entropy E(w, wo|X) = − Σ[rt log yt + (1 −
rt) log(1 — y¹)] and yt = tanh(w²xt + wo), derive the update for w; where j ‡ 0.
Note: Given y tanh(a), the derivative
=
Əy
да
= 1- y².
Transcribed Image Text:4. In linear discrimination, gradient descent is used to find the minimum of the error function. With error function defined as the cross entropy E(w, wo|X) = − Σ[rt log yt + (1 − rt) log(1 — y¹)] and yt = tanh(w²xt + wo), derive the update for w; where j ‡ 0. Note: Given y tanh(a), the derivative = Əy да = 1- y².
Expert Solution
steps

Step by step

Solved in 2 steps with 2 images

Blurred answer
Recommended textbooks for you
Algebra & Trigonometry with Analytic Geometry
Algebra & Trigonometry with Analytic Geometry
Algebra
ISBN:
9781133382119
Author:
Swokowski
Publisher:
Cengage
Algebra and Trigonometry (MindTap Course List)
Algebra and Trigonometry (MindTap Course List)
Algebra
ISBN:
9781305071742
Author:
James Stewart, Lothar Redlin, Saleem Watson
Publisher:
Cengage Learning