On The Dynamic Ensemble Selection for TinyML-based Systems -- a Preliminary Study
This addresses the problem of optimizing machine learning for resource-constrained TinyML systems, but it is incremental as it explores an existing method in a new context.
The study tackled the challenge of balancing inference time and classification quality in TinyML systems by examining a Dynamic Ensemble Selection (DES)-Clustering approach for a multi-class computer vision task, showing that a larger pool of classifiers improves accuracy but increases average inference time.
The recent progress in TinyML technologies triggers the need to address the challenge of balancing inference time and classification quality. TinyML systems are defined by specific constraints in computation, memory and energy. These constraints emphasize the need for specialized optimization techniques when implementing Machine Learning (ML) applications on such platforms. While deep neural networks are widely used in TinyML, the exploration of Dynamic Ensemble Selection (DES) methods is also beneficial. This study examines a DES-Clustering approach for a multi-class computer vision task within TinyML systems. This method allows for adjusting classification accuracy, thereby affecting latency and energy consumption per inference. We implemented the TinyDES-Clustering library, optimized for embedded system limitations. Experiments have shown that a larger pool of classifiers for dynamic selection improves classification accuracy, and thus leads to an increase in average inference time on the TinyML device.