Generating Efficient DNN-Ensembles with Evolutionary Computation
This work addresses the need for efficient deep learning models in image classification, offering a method that outperforms state-of-the-art automatic model generation by being 5.6x faster, though it is incremental as it builds on existing ensemble strategies.
The paper tackled the problem of creating faster, smaller, and more accurate deep learning models by jointly optimizing accuracy, inference time, and parameters using ensemble learning, resulting in models with speedups up to 7.60x, parameter reductions by 10x, or accuracy increases up to 6.01% compared to the best DNN in the pool.
In this work, we leverage ensemble learning as a tool for the creation of faster, smaller, and more accurate deep learning models. We demonstrate that we can jointly optimize for accuracy, inference time, and the number of parameters by combining DNN classifiers. To achieve this, we combine multiple ensemble strategies: bagging, boosting, and an ordered chain of classifiers. To reduce the number of DNN ensemble evaluations during the search, we propose EARN, an evolutionary approach that optimizes the ensemble according to three objectives regarding the constraints specified by the user. We run EARN on 10 image classification datasets with an initial pool of 32 state-of-the-art DCNN on both CPU and GPU platforms, and we generate models with speedups up to $7.60\times$, reductions of parameters by $10\times$, or increases in accuracy up to $6.01\%$ regarding the best DNN in the pool. In addition, our method generates models that are $5.6\times$ faster than the state-of-the-art methods for automatic model generation.