CPU Cache Lines: The Unit of Memory Transfer
Explore how CPU cache lines work, understand spatial locality, and see why memory access patterns dramatically impact performance through interactive visualizations.
No direct links0 refs
ML Concepts - Page 12
Clear explanations of core machine learning concepts, from foundational ideas to advanced techniques. Understand attention mechanisms, transformers, skip connections, and more.
167
Total Concepts
274
Topics
Page 12
of 28
Concepts - Page 12
Contrastive Loss Functions
Master contrastive loss functions including InfoNCE, NT-Xent, and Triplet Loss for representation learning and self-supervised training.
No direct links0 refs
Focal Loss for Imbalanced Classification
Master focal loss, the game-changing loss function that addresses extreme class imbalance by down-weighting easy examples and focusing on hard negatives.
No direct links0 refs
KL Divergence
Understand Kullback-Leibler divergence, the fundamental measure of difference between probability distributions used in VAEs, information theory, and model compression.
No direct links0 refs
Dropout Regularization
Master dropout, the powerful regularization technique that prevents overfitting by randomly deactivating neurons during training, creating an ensemble of sub-networks.
No direct links0 refs
Context Windows: The Memory Limits of LLMs
Interactive visualization of context window mechanisms in LLMs - sliding windows, expanding contexts, and attention patterns that define what models can "remember".
No direct links0 refs
Showing 67-72 of 167 articles