Home Courses Cancer Diagnosis using Medical Records Loss function (Hinge Loss) based interpretation

Loss function (Hinge Loss) based interpretation

Instructor: Applied AI Course Duration: 18 mins

This content is restricted. Please Login

Prev

Next

Mathematical derivation

RBF-Kernel

Support Vector Machines (SVM)

1.1

Geometric Intution

20 min

1.2

Mathematical derivation

32 min

1.3

Loss function (Hinge Loss) based interpretation

18 min

1.4

21 min

1.5

Polynomial kernel

11 min

1.6

Domain specific Kernels

6 min

1.7

Train and run time complexities

8 min

1.8

nu-SVM: control errors and support vectors

6 min

1.9

8 min

1.10

14 min

1.11

Exercise: Apply SVM to Amazon reviews dataset

4 min

1.12

Why we take values +1 and and -1 for Support vector planes

9 min

1.13

Dual form of SVM formulation

16 min

1.14

10 min

1.15

9 min

Ensemble Models

2.1

Introduction to Bootstrapped Aggregation (Bagging)

17 min

2.2

Random Forest and their construction

15 min

2.3

Bias-Variance tradeoff(Random Forest)

7 min

2.4

Intution to Boosting

17 min

2.5

Gradient Boosting

10 min

2.6

AdaBoost: geometric intuition

7 min

2.7

Stacking models

22 min

2.8

Exercise: Apply GBDT and RF to Amazon reviews dataset

4 min

2.9

What are ensembles?

6 min

2.10

Bagging :Train and Run-time Complexity.

9 min

2.11

Bagging:Code Sample

4 min

2.12

Extremely randomized trees

8 min

2.13

Random Tree :Cases

6 min

2.14

Residuals, Loss functions and gradients

13 min

2.15

Regularization by Shrinkage

8 min

2.16

Train and Run time complexity

6 min

2.17

XGBoost: Boosting + Randomization

14 min

2.18

Cascading classifiers

15 min

2.19

Kaggle competitions vs Real world

9 min