神经进化系统中的物理合理性研究
Towards Physical Plausibility in Neuroevolution Systems
AI总结:
针对AI模型推理阶段的高能耗问题,本研究提出将功耗纳入适应度函数的神经进化框架,结合新型突变策略与双模型训练技术,实现ANN模型功耗最高降低29.2%且性能无显著下降。
摘要:
人工智能(AI)模型尤其是深度神经网络(DNN)的应用日益广泛,导致训练和推理阶段的功耗不断上升,引发了环境问题,也推动了对更节能算法和硬件解决方案的需求。本研究针对机器学习(ML)中尤其是推理阶段日益严重的能耗问题展开,哪怕功耗仅有小幅降低,也能带来显著的能源节约,惠及用户、企业与环境。我们的方法聚焦于在神经进化框架下最大化人工神经网络(ANN)模型的准确率,同时最小化其功耗,为此将功耗纳入适应度函数的考量。我们提出了一种新的突变策略,可随机重新引入层模块,其中节能模块被选中的概率更高;还提出了一项新技术,能在单个训练步骤中训练两个独立模型,同时推动其中一个在保持相近准确率的前提下比另一个更节能。实验结果表明,该方法可使ANN模型的功耗降低多达29.2%,且预测性能无显著下降。
英文摘要:
The increasing usage of Artificial Intelligence (AI) models, especially Deep Neural Networks (DNNs), is increasing the power consumption during training and inference, posing environmental concerns and driving the need for more energy-efficient algorithms and hardware solutions. This work addresses the growing energy consumption problem in Machine Learning (ML), particularly during the inference phase. Even a slight reduction in power usage can lead to significant energy savings, benefiting users, companies, and the environment. Our approach focuses on maximizing the accuracy of Artificial Neural Network (ANN) models using a neuroevolutionary framework whilst minimizing their power consumption. To do so, power consumption is considered in the fitness function. We introduce a new mutation strategy that stochastically reintroduces modules of layers, with power-efficient modules having a higher chance of being chosen. We introduce a novel technique that allows training two separate models in a single training step whilst promoting one of them to be more power efficient than the other while maintaining similar accuracy. The results demonstrate a reduction in power consumption of ANN models by up to 29.2% without a significant decrease in predictive performance.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。