L8.3 Logistic Regression Loss Derivative and Training

preview_player
Показать описание

Now that we understand the forward pass in logistic regression and are familiar with the loss function, let us look at the loss derivative (or gradient) with respect to the weights. Then we can apply gradient descent to update the weights to minimize the loss and thereby optimize the prediction accuracy.

-------

This video is part of my Introduction of Deep Learning course.

-------

  1. Sebastian Raschka
  2. deep learning
Рекомендации по теме
L8.3 Logistic Regression 0:19:57

L8.3 Logistic Regression Loss Derivative and Training

L8.2 Logistic Regression 0:12:57

L8.2 Logistic Regression Loss Function

Derivative of Cost 0:08:34

Derivative of Cost function for Logistic Regression | Machine Learning

Linear vs Logistic 0:27:07

Linear vs Logistic Regression; Derivative of their Loss Functions

L8.0 Logistic Regression 0:06:28

L8.0 Logistic Regression -- Lecture Overview

derivative of cost 0:07:51

derivative of cost function for Logistic Regression (7 Solutions!!)

41 Logistic Regression 0:09:24

41 Logistic Regression - Log Loss & Binary Cross Entropy Cost Function

7.2.3. Loss Function 0:29:13

7.2.3. Loss Function and Cost Function for Logistic Regression

L8.8 Softmax Regression 0:19:40

L8.8 Softmax Regression Derivatives for Gradient Descent

Logistic Regression: Loss 0:07:08

Logistic Regression: Loss function

04 03 Backpropagation 0:02:11

04 03 Backpropagation and Logistic Regression

Logistic Regression: Optimization 0:12:36

Logistic Regression: Optimization

Machine learning: Minimizing 0:17:47

Machine learning: Minimizing Logistic Regression cost function!

Understanding Binary Cross-Entropy 0:05:21

Understanding Binary Cross-Entropy / Log Loss in 5 minutes: a visual explanation

Mathematics: Derivative of 0:02:15

Mathematics: Derivative of Softmax loss function

Logistic Regression | 0:11:44

Logistic Regression | How to derive Logistic Regression | Deriving Logistic Regression Equation - P5

Beta Derivatives of 0:10:08

Beta Derivatives of MSE | ML Course 2.7

Logistic regression 1: 0:13:36

Logistic regression 1: Model and loss

Cost Function and 0:18:15

Cost Function and Gradient Descent in Logistic Regression Machine Learning

Lecture10. Loss Function 1:02:36

Lecture10. Loss Function Optimality

L15 - LOSS 0:17:35

L15 - LOSS FUNCTION FOR REGRESSION PROBLEM || MACHINE LEARNING - BASIC TO ADVANCE.

Lec 2.3: Computational 0:13:59

Lec 2.3: Computational Graphs for Logistic Regression

Lecture #21: Vectorizing 0:13:45

Lecture #21: Vectorizing Logistic Regression Backpropagation | Deep Learning

How to derive 0:09:01

How to derive the Equation for Logistic Regression

Комментарии
Автор

Is the neg log likelihood function in the 5:00 wrong? It should be a negative sign in the second term, which is -(1-yi)?

jiangshaowen
Автор

At 11:44, when you take the derivative, should it be 1/n * (y - yhat) since you are taking derivative with respect to y? Did you miss a negative sign?

algorithmo