Deep Learning (DL) has advanced various fields by extracting complex patterns from large datasets. However, the computational demands of DL models pose environmental and resource challenges. Deep shift neural networks (DSNNs) offer a solution by leveraging shift operations to reduce computational complexity at inference. Following the insights from standard DNNs, we are interested in leveraging the full potential of DSNNs by means of AutoML techniques. We study the impact of hyperparameter optimization (HPO) to maximize DSNN performance while minimizing resource consumption. Since this combines multi-objective (MO) optimization with accuracy and energy consumption as potentially complementary objectives, we propose to combine state-of-the-art multi-fidelity (MF) HPO with multi-objective optimization. Experimental results demonstrate the effectiveness of our approach, resulting in models with over 80\% in accuracy and low computational cost. Overall, our method accelerates efficient model development while enabling sustainable AI applications.

翻译：深度学习通过从大规模数据集中提取复杂模式，推动了多个领域的发展。然而，深度学习模型的计算需求带来了环境和资源方面的挑战。深度移位神经网络通过利用移位操作降低推理时的计算复杂度，提供了一种解决方案。基于标准深度神经网络的洞见，我们致力于通过自动机器学习技术充分挖掘深度移位神经网络的潜力。我们研究了超参数优化的影响，以在最小化资源消耗的同时最大化深度移位神经网络的性能。由于这结合了多目标优化（以准确率和能量消耗作为潜在互补目标），我们提出将最先进的多保真度超参数优化与多目标优化相结合。实验结果表明了该方法的有效性，生成的模型准确率超过80%且计算成本较低。总体而言，我们的方法加速了高效模型开发，同时实现了可持续的人工智能应用。