Articles by tag: ml-optimization

CMA-ES in Optuna: hyperparameter optimization without gradients

Step-by-step breakdown of CMA-ES — an evolutionary algorithm for hyperparameter selection. How step adaptation and covariance matrix work. Examples and recommendations.

TAPe detection: 100k parameters vs SOTA models

How the TAPe detector with 100k parameters outperforms YOLO and RF-DETR in speed and resource savings. Detailed breakdown of benchmarks and advantages for developers.