AI Study Hub
Curated core theories and essential concepts to strengthen the fundamentals.
Summarizes how neural networks learn rules from data and the key ideas of optimization and gradient descent that make this possible.
Summarizes the structure of multilayer perceptrons, activation functions, binary/multi-class classification and regression, and model scaling β all in one place.
Review experiments and paper summaries to capture insights quickly.
Quick reference for normalization, standardization, regularization, and generalization
Study notes on the Generative Adversarial Nets (GAN) paper