A Short Introduction to Entropy, Cross-Entropy and KL-Divergence
Entropy, Cross-Entropy and KL-Divergence are often used in Machine Learning, in particular for training classifiers. In this short video, you will understand where they come from and why we use them in ML.
Paper:
- "A mathematical theory of communication", Claude E. Shannon, 1948, http://pubman.mpdl.mpg.de/pubman/item/escidoc:2383164/component/escidoc:2383163/Shannon_Weaver_1949_Mathematical.pdf
Errata:
* At 5:05, the sign is reversed on the second line, it should read: "Entropy = -0.35 log2(0.35) - ... - 0.01 log2(0.01) = 2.23 bits"
The painting on the first slide is by Annie Clavel, a great French artist currently living in Los Angeles. The painting is reproduced with her kind authorization. Please visit her website: http://www.annieclavel.com/.
Видео A Short Introduction to Entropy, Cross-Entropy and KL-Divergence канала Aurélien Géron
Paper:
- "A mathematical theory of communication", Claude E. Shannon, 1948, http://pubman.mpdl.mpg.de/pubman/item/escidoc:2383164/component/escidoc:2383163/Shannon_Weaver_1949_Mathematical.pdf
Errata:
* At 5:05, the sign is reversed on the second line, it should read: "Entropy = -0.35 log2(0.35) - ... - 0.01 log2(0.01) = 2.23 bits"
The painting on the first slide is by Annie Clavel, a great French artist currently living in Los Angeles. The painting is reproduced with her kind authorization. Please visit her website: http://www.annieclavel.com/.
Видео A Short Introduction to Entropy, Cross-Entropy and KL-Divergence канала Aurélien Géron
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Variational AutoencodersIntuitively Understanding the KL DivergenceA better description of entropyInformation entropy | Journey into information theory | Computer Science | Khan AcademyA friendly introduction to Bayes Theorem and Hidden Markov ModelsWhy do we need Cross Entropy Loss? (Visualized)What is meant by entropy in statistics?Capsule Networks (CapsNets) – TutorialHow to Analyze a Rental Property (No Calculators or Spreadsheets Needed!)ROC and AUC, Clearly Explained!What is entropy? - Jeff PhillipsSynthetic Gradients Tutorial - How to Speed Up Deep Learning Training015 Jensen's inequality & Kullback Leibler divergenceShannon Entropy and Information GainIntro to Information Theory | Digital Communication | Information TechnologyStatQuest: Principal Component Analysis (PCA), Step-by-StepGradient descent, how neural networks learn | Chapter 2, Deep learningWhat is KL Divergence?Stanford Seminar - Information Theory of Deep LearningTensorFlow 2.0 Changes