Toggle navigation sidebar
Toggle in-page Table of Contents
Keto | Data Science
Data Science
CS 189 Review
Design and Bias
Naive Bayes
Quadratic Program
Bayesian Inference
Hypothesis Testing
Likelihood Ratio
Integrators
Numerical Integration
Optimizers
Adaptive Boosting
Convex Function
Cross Entropy
Feature Scaling
Gradient Descent
Line Search Methods
Linear Program
Loss Function
Newton’s Method
Quadratic Program
Probability Theory
Examples
Frequentist vs Bayesian
Probability Generating Function
Sampling without Replacement
Expected Value
Combinatorics
Rules of Counting
Concentration Inequality
Chebyshev’s Inequality
Chernoff Inequality
Law of Large Numbers
Markov’s Inequality
Continuous Distribution
Beta Distribution
Chi-Square Distribution
Cumulative Distribution Function
Exponential Decay Distribution
Gamma Distribution
Gaussian or Normal Distribution
Introduction
Joint Density
Probability Density Function
Uniform (Continuous)
Discrete Distributions
Bernoulli
Binomial
Geometric Distribution
Hypergeometric
Poisson Distribution
Sampling Without Replacement
Distribution of Sums
Average
Central Limit Theorem
Independent Identically Distributed Sums
Mean Squared Error
Markov-Chain
Detailed Balance
Introduction
Markov Chain Monte Carlo
Matrix Formalism
Properties
Reversible Process
Probability
Axioms
Conditional Probability
Joint Probability
Outcome Space and Events
Probability Scenarios
Random-Variable
Random Variable
Random Variable
Random Vectors
Sampling Estimation
Confidence Intervals
Estimators
Summary-Statistics
Cumulants and Moments
Expected Value
Variance
Transformation
Introduction
Statistical Modelling
Bias Variance Tradeoff
Classification
Centroid Method
Introduction to Support Vector Machine
k-Nearest Neighbors
Maximal Margin Classifier
Non-linear Classificaton
Percepton Algorithm
Support Vector Classifier
Clustering
Introduction to Clustering
k-means Clustering
Spectral Graph Clustering
Decision Trees
Ensemble Learning
Introduction
Random Forest
Regression Tree
Dimensionality Reduction
Principle Component Analysis
Discrimnant Analysis
Gaussian Discrimnant Analysis
Linear Discriminant Analysis
Quadratic Discriminant Analysis
Feature Engineering
Feature Selection
Kernels
Gaussian Kernel
Introduction
Kernel Logistic Regression
Kernel Perceptron
Kernel Ridge Regression
Kernel Trick
Neural Networks
Activation Functions
Convolution Layer
Convolutional Neural Networks
Fully Connected Layer
Heuristics
Introduction
Neurons
Training
Vanishing Gradient Problem
Probabilistic Models
Bayes Decision Rule
Bayesian Update
Introduction
Uniform Prior
Maximum Likelihood Estimator
Posterior Estimator
Prediction by Expectation
Probabilistic Linear Regression
Sampling Probability
Regression
Lasso Regression
Least Squares Regression
Linear Model
Linear Regression
Logistics Regression
Ridge Regression
.md
.pdf
Contents
Softmax Function
Activation Functions
Contents
Softmax Function
Activation Functions
#
Softmax Function
#
The softmax function is similar to the sigmoid function but for multiple classes.
\[ z_j = \frac{e^{h_j}}{\sum_{i=1}^k e^{h_i}} \]