
Optimized Ensemble Learning for Classification
Two deliberately lopsided models — one that never calls a positive wrongly, one that never misses a positive — and a meta-model that reads both.
Python · XGBoost · TensorFlow · Ensemble methods
2projects · all work

Two deliberately lopsided models — one that never calls a positive wrongly, one that never misses a positive — and a meta-model that reads both.
Python · XGBoost · TensorFlow · Ensemble methods

Retraining SSD-MobileNet detectors on small custom datasets, and measuring how much of the feature extractor is worth freezing — the answer was the first four blocks.
TensorFlow · Object Detection API · Keras · MobileNet