Why Do We Use the Sigmoid Function for Binary Classification?
This video explains why we use the sigmoid function in neural networks for machine learning, especially for binary classification. We consider both the practical side of making sure we get a consistent gradient from the standard categorical loss function, as well as making sure the equation is easily computable. We also look at the statistical side by giving an interpretation for what the logit values represent (the values passed into the sigmoid function), and how they can be thought of as normally distributed values with their means shifted one way or the other depending on which class they are for.
My other video, "Derivative of Sigmoid and Softmax Explained Visually":
📼 https://youtu.be/gRr2Q97XS2g
The Desmos graph of the sigmoid function:
📈https://www.desmos.com/calculator/hjc4peyxmc
Connect with me:
🐦 Twitter - https://twitter.com/elliotwaite
📷 Instagram - https://www.instagram.com/elliotwaite
👱 Facebook - https://www.facebook.com/elliotwaite
💼 LinkedIn - https://www.linkedin.com/in/elliotwaite
Join our Discord community:
💬 https://discord.gg/cdQhRgw
🎵 Kazukii - Return
→ https://soundcloud.com/ohthatkazuki
→ https://open.spotify.com/artist/5d07MpiIaNmmEMTq79KAga
→ https://www.youtube.com/user/OfficialKazuki
Видео Why Do We Use the Sigmoid Function for Binary Classification? канала Elliot Waite
My other video, "Derivative of Sigmoid and Softmax Explained Visually":
📼 https://youtu.be/gRr2Q97XS2g
The Desmos graph of the sigmoid function:
📈https://www.desmos.com/calculator/hjc4peyxmc
Connect with me:
🐦 Twitter - https://twitter.com/elliotwaite
📷 Instagram - https://www.instagram.com/elliotwaite
👱 Facebook - https://www.facebook.com/elliotwaite
💼 LinkedIn - https://www.linkedin.com/in/elliotwaite
Join our Discord community:
💬 https://discord.gg/cdQhRgw
🎵 Kazukii - Return
→ https://soundcloud.com/ohthatkazuki
→ https://open.spotify.com/artist/5d07MpiIaNmmEMTq79KAga
→ https://www.youtube.com/user/OfficialKazuki
Видео Why Do We Use the Sigmoid Function for Binary Classification? канала Elliot Waite
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
The Sigmoid : Data Science BasicsSoftmax Function Explained In Depth with 3D VisualsStatQuest: Logistic RegressionWhich Activation Function Should I Use?Activation Functions - EXPLAINED!But what is a neural network? | Chapter 1, Deep learningAll the Numbers - NumberphileWhat is backpropagation really doing? | Chapter 3, Deep learningDerivative of Sigmoid and Softmax Explained VisuallyThis Neural Network Learned To Look Around In Real Scenes!Why Does This Pattern Emerge?PyTorch Autograd Explained - In-depth TutorialThe Sigmoid Function Clearly ExplainedROC and AUC, Clearly Explained!Policy Gradient Theorem Explained - Reinforcement LearningDeep Q-Network & Dueling network architectures for deep reinforcement learningCellular Automata: Rule 30 + Conway’s Game of LifeSigmoid function Explained in simplest wayDerivative of the Sigmoid Activation function | Deep LearningMachine Learning Tutorial Python - 8: Logistic Regression (Binary Classification)