CS231n

system input: images, predermined category labelswhat computer really seas: just a grid our classification algorithm should be robust at different kin

Lecture 3 continues our discussion of linear classifiers. We introduce the idea of a loss function to quantify our unhappiness with a model’s predicti

In Lecture 4 we progress from linear classifiers to fully-connected neural networks. We introduce the backpropagation algorithm for computing gradient

Activation functions, Data Preprocessing, Weight Initialization, Batch Normalization, Hyperparameter Optimization

Optimization, Regularization, Transfer Learning

In Lecture 9 we discuss some common architectures for convolutional neural networks. We discuss architectures which performed well in the ImageNet cha