The Conception Of Machine Learninng

the conception of Machine Learning 1

Hidden layer

Heteroskedasticity

Hessian Matrix

Hyperparameter tuning

How To Choose Hidden Unit Activiation Functions

Bias-Variance Tradeoff

alpha in ridge regression

Bootstrapping, Transmission Gate

capacity

Common Optimizers of Neural Nets

K-Fold Cross-Validation

Common Output Layer Activation Functions

Concave & convex function

cross-entropy

conditional probability

Cost and Lost Functions

Confidence Intervals

F1



Exploding Gradient Problem

error type

Finding Linear Regression Parameters

Gradient Descent

Gradient Descent rule of thume

The Unknow Word

The First Column	The Second Column
thume

转载于:https://www.cnblogs.com/hugeng007/p/9459682.html