For this first reading group on the Stanford University Convolutional Neural Networks class, we went through the following slides:
- Image classification, data-driven approach, k-nearest neighbor
- Linear classification: SVM/Softmax
- Optimization, higher-level representations, image features (first half)
There are two loss functions commonly used: the softmax and the SVM. In order to optimize the weights and train effectively, we will want to minimize the chosen loss function during training.