to use log-transform: when data is right-skewed or spans multiple orders of magnitude

log-probabilities are used instead of probabilities: avoids numerical underflow

Log-probabilities convert multiplications into additions, preventing numerical underflow

to use an RNN/LSTM: for sequential data where order matters (mostly replaced by transformers)

Use RNN/LSTM for sequential data where order matters (mostly replaced by transformers)

log-loss / cross-entropy loss penalizes: confident wrong predictions more heavily

Log-loss penalizes confident incorrect predictions more heavily

sinusoidal position encoding works: each dimension has a different frequency

Sinusoidal position encoding assigns unique frequencies to each dimension, enabling the model to distinguish positions effectively

Cross-entropy

Cross-entropy loss equation: H(p, q) = -Σ(p(x) * log(q(x)))

to use XGBoost: for tabular data where you want the best possible performance

Use XGBoost for high-performance predictions on structured tabular data