In recent years, Deep Learning models have shown a great performance in complex optimization problems. They generally require large training datasets, which is a limitation in most practical cases. Transfer learning allows importing the first layers of a pre-trained architecture and connecting them to fully-connected layers to adapt them to a new problem. Consequently, the configuration of the these layers becomes crucial for the performance of the model. Unfortunately, the optimization of these models is usually a computationally demanding task. One strategy to optimize Deep Learning models is the pruning scheme. Pruning methods are focused on reducing the complexity of the network, assuming an expected performance penalty of the model once pruned. However, the pruning could potentially be used to improve the performance, using an optimization algorithm to identify and eventually remove unnecessary connections among neurons. This work proposes EvoPruneDeepTL, an evolutionary pruning model for Transfer Learning based Deep Neural Networks which replaces the last fully-connected layers with sparse layers optimized by a genetic algorithm. Depending on its solution encoding strategy, our proposed model can either perform optimized pruning or feature selection over the densely connected part of the neural network. We carry out different experiments with several datasets to assess the benefits of our proposal. Results show the contribution of EvoPruneDeepTL and feature selection to the overall computational efficiency of the network as a result of the optimization process. In particular, the accuracy is improved, reducing at the same time the number of active neurons in the final layers.

翻译：近年来，深度学习模型在复杂优化问题中展现出卓越性能，但其通常需要大规模训练数据集，这在大多数实际应用中构成限制。迁移学习允许导入预训练架构的前几层，并将其与全连接层连接以适配新问题。因此，这些层的配置对模型性能至关重要。然而，这些模型的优化通常是计算密集型任务。剪枝策略是优化深度学习模型的一种方法，其旨在降低网络复杂度，但通常会导致模型性能下降。然而，剪枝方法若能借助优化算法识别并最终移除神经元间不必要的连接，则可能用于提升性能。本文提出EvoPruneDeepTL——一种面向基于迁移学习的深度神经网络的进化剪枝模型，该模型用遗传算法优化的稀疏层替换最后的全连接层。根据其解编码策略，所提模型可对神经网络的密集连接部分执行优化剪枝或特征选择。我们通过多个数据集开展实验以评估所提方法的优势。结果表明，EvoPruneDeepTL与特征选择通过优化过程提升了网络的整体计算效率。具体而言，模型在减少最终层活跃神经元数量的同时，提高了分类准确率。