본문으로 이동
Scientific Inference Lab
기계학습개론
What a Model
Learns
↗
Learning from
Data
↗
Statistical Learning
Learning Types
Data and Learning Types
Labels, Structure,
Rewards
↗
Learning Problems
Supervised Data
Actions and Rewards
Outputs, Structure, and Rewards
Vectors and
Matrices
↗
Vectors
Dot Products
Matrix Multiplication
Vectors and Matrices
Derivatives and
Probability
↗
Derivatives
Gradients
Probability Distributions
Derivatives and Probability
Learning and
Generalization
↗
Training and Test Data
Prediction Error
Model Complexity
Learning and Generalization
Data
Leakage
↗
Raw Data Preparation
Data Leakage
Pipelines
Data Leakage and Pipelines
Linear
Models
↗
Linear Regression
Least Squares
Linear Models
Predicting a
Probability
↗
Logistic Regression
Probability to Decision
Logistic Regression
Walking
Downhill
↗
Objective Functions
Gradient Descent
Gradient Descent
Fewer Examples per
Step
↗
Stochastic Gradient Descent
Mini-batches and Epochs
Stochastic Gradient Descent
The
Perceptron
↗
Perceptron Prediction
Perceptron Learning Rule
Perceptrons
One Line Is Not
Enough
↗
Linear Separability
XOR
Linear Separability
Stacking the
Layers
↗
Hidden Layers
Activation Functions
Forward Pass
Multilayer Perceptrons
Working
Backwards
↗
Computational Graphs
Chain Rule
Backpropagation
Backpropagation
One Split Is One Sample
Counting the Mistakes
