Softmax function
The softmax function, also known as softargmax: 184 or normalized exponential function,: 198 converts a vector of K real numbers into a probability distribution of K possible outcomes. It is a generalization of the logistic function to multiple dimensions, and used in multinomial logistic regression. The softmax function is often used as the last activation function of a neural network to normalize the output of a network to a probability distribution over predicted output classes, based on Luce's choice axiom.
Softmax function - Wikipedia Jump to content From Wikipedia, the free encyclopedia Smooth approximation of one-hot arg max This article is about the smooth approximation of one-hot arg max. For the smooth approximations of max, see Smooth maximum . "Softmax" redirects here. For the Korean video game company, see ESA (company) . Part of a series on Machine learning and data mining Paradigms Supervised learning Unsupervised learning Semi-supervised learning Self-supervised learning Reinforcement learning Meta-learning Online learning Batch learning Curriculum learning Rule-based learning Neuro-s
Explore this link on the map →related reading
- Understanding the Softmax Activation Function: A Comprehensive Guidesinglestore.com
- Understanding softmax and the negative log-likelihoodljvmiranda921.github.io
- Attention Is Off By One – Evan Millerevanmiller.org
- 使用 TensorFlow 學習 Softmax 回歸 (Softmax Regression) | by Leo Chiu | 手寫筆記 | Mediummedium.com
- Neural networks and deep learningneuralnetworksanddeeplearning.com
- Deriving Muonjeremybernste.in
- Fabian Fuchsfabianfuchsml.github.io
- YC's Note – 剖析深度學習 (4)：Sigmoid, Softmax怎麼來？為什麼要用MSE和Cross Entropy？談廣義線性模型ycc.idv.tw
- Sigmoid function - Wikipediaen.wikipedia.org
- CS231n Deep Learning for Computer Visioncs231n.github.io
- Neural networks and deep learningneuralnetworksanddeeplearning.com
- Support vector machine - Wikipediaen.wikipedia.org