Archive
48 Posts
Connections: Log Likelihood, Cross Entropy, KL Divergence, Logistic Regression, and Neural Networks
Guided Grad-CAM is Broken! Sanity Checks for Saliency Maps
CNN Heat Maps: Gradients vs. DeconvNets vs. Guided Backpropagation
Best Use of Train/Val/Test Splits, with Tips for Medical Data
Universal Transformers
The Transformer: Attention Is All You Need
Learn to Pay Attention! Trainable Visual Attention in CNNs
Convolution vs. Cross-Correlation
