System und Verfahren zum Trainieren von Maschinenlernmodellen

Details

Veröffentlichungs-Nr.

EP4715675

Anmeldetag

22. September 2025

Veröffentlichung

25. März 2026

Rechtsraum

EP

Abstract

A system and method are disclosed for training and optimizing machine learning models for computer vision using mixed activation functions across model layers. A baseline model is received and a search space of candidate activation functions is defined. For each candidate substitution, a zero-cost accuracy score is computed without full training, and latency and memory costs are benchmarked across target hardware devices. Using this information, an optimization process such as random search, integer linear programming, or Local Zero Cost Maxima selects a layer-specific configuration of mixed activation functions that satisfies application constraints including accuracy, latency, and memory budgets. The selected model is then trained or fine-tuned to produce an optimized model. Experimental results on YOLO architectures demonstrate improved mean Average Precision, lower latency, and reduced memory usage relative to baseline models. This approach enables efficient deployment of computer vision models across CPUs, GPUs, and neural processing units.

Anmelder

Firma

STMicroelectronics International N.V.

Land

🇨🇭 Schweiz