Machine Learning 101: The Confusion Matrix

preview_player
Показать описание
Machine Learning 101: The Confusion Matrix

Machine Learning is the use and development of computer systems that are able to learn and adapt without following explicit instructions, by using algorithms and statistical models to analyze and draw inferences from patterns in data.

The confusion matrix helps assess classification model performance in machine learning by comparing predicted values against actual values for a dataset. A confusion matrix (or, error matrix) is a visualization method for classifier algorithm results (IBM).

This video goes over the basics of confusion matrix, to aid in understanding more complex machine learning concepts in the future. Confusion Matrices are useful for cybersecurity related classification, such as identifying malicious URLs, behavior, traffic, IPs, and more.

----------------------------------------------------------------------------------

Timeline:
0:00 The usecase
2:05 Feature Analysis in ML
3:46 ML Models to choose from
5:25 2-class confusion matrix
7:47 2-class matrix for each model
9:23 Multi-class confusion matrix
15:29 Calculating Accuracy, Precision, and Recall

----------------------------------------------------------------------------------

Video Editor:

----------------------------------------------------------------------------------

Socials:
Discord: @vipv4

----------------------------------------------------------------------------------

Join our community!
Рекомендации по теме
Комментарии
Автор

Awesome video! It's always hard to start learning something new without knowing the terminology. Hope you continue this series :D

JerryThings
Автор

Great video, thank you!
15:28 You forgot some parentheses here:
Precision = TP / (TP + FP)
Recall = TP / (TP + FN)

SpaceSpaceCat