CS231n - Lec2. Image Classification

First classifier :

Nearest Neighbor Classifier 

Train O(1)

Predict O(N) 

 

Setting hyperparameters 

#1

Choose hyperparameters that work best on the data 

#2

Split data into train and test, choose hyperparameters that work best on test data 

#3 

Split data into train, val, and test; choose hyperparameters on val and evaluate on test 

#4

Cross-Validation: split data into folds, try each fold as validation and average the results 

 

f(x,W)=Wx+b

x : 32X32X3 => 3072X1

W : 10X3072

Wx => 10

b : 10X1