JJ

Home

❯

AI

❯

Fundamentals

Fundamentals

  • Batch Size and Epochs

    • Decoding Strategies

      • Distributed Data Parallel (DDP)

        • Dropout and Coadaptation

          • Early Stopping

            • Ensemble Methods (Bagging, Boosting)

              • Entropy

                • Gradient Clipping

                  • Gradient Descent

                    • Hyperparameter Tuning

                      • K-Fold Cross-Validation

                        • Kullback-Liebler Divergence (KL Divergence)

                          • Label Smoothing

                            • Learning Rate

                              • Loss Functions

                                • Machine Learning Paradigms

                                  • Mixed Precision Training

                                    • Multilayer Perceptrons (MLP)

                                      • Multiple Instance Learning (MIL)

                                        • Neurons

                                          • Optimisers

                                            • Pretraining Data Curation

                                              • Pretraining Loop

                                                • Random Forest

                                                  • ReLU and Gated Activations

                                                    • Sampling

                                                      • Scaling Laws

                                                        • Softmax

                                                          • SpecAugment

                                                            • Teacher Forcing

                                                              • Vanishing Gradient Problem

                                                                • Weight Decay


                                                                  Created with Quartz v5.0.0 © 2026