Focal Loss: Focusing on Hard Examples
Learn focal loss for deep learning: down-weight easy examples, focus on hard ones. Interactive demos of gamma, alpha balancing, and RetinaNet.
No direct links0 refs
ML Concepts - Page 21
Clear explanations of core machine learning concepts, from foundational ideas to advanced techniques. Understand attention mechanisms, transformers, skip connections, and more.
189
Total Concepts
357
Topics
Page 21
of 32
Concepts - Page 21
He/Kaiming Initialization
Learn He (Kaiming) initialization for ReLU networks: why ReLU needs special weight initialization, variance flow, and dead neurons explained.
No direct links0 refs
KL Divergence in Machine Learning
Learn KL divergence for machine learning: measure distribution differences in VAEs, knowledge distillation, and variational inference.
No direct links0 refs
MSE and MAE Loss Functions
Interactive guide to MSE vs MAE for regression: explore outlier sensitivity, gradient behavior, and Huber loss with visualizations.
No direct links0 refs
Xavier/Glorot Initialization
Learn Xavier (Glorot) initialization: how it balances forward signals and backward gradients to enable stable deep network training with tanh and sigmoid.
No direct links0 refs
ALiBi: Attention with Linear Biases
Learn ALiBi, the position encoding method that adds linear biases to attention scores for exceptional length extrapolation in transformers.
No direct links0 refs
Showing 121-126 of 189 articles