深度学习的降低精度策略:高能物理生成对抗网络用例
Reduced Precision Strategies for Deep Learning: A High Energy Physics Generative Adversarial Network Use Case
摘要:
深度学习正在通过取代传统的蒙特卡罗模拟进入高能物理领域。然而,深度学习仍然需要大量的计算资源。使深度学习更有效的一种有希望的方法是将神经网络的参数降到更低的精度。降低精度计算广泛用于现代深度学习,并导致更低的执行推理时间,更小的内存占用和更少的内存带宽。在本文中,我们分析了低精度推理对复杂的深度生成对抗网络模型的影响。我们正在解决的用例是基于加速器的高能物理中亚原子粒子相互作用的量热计检测器模拟。我们采用新型英特尔低精度优化工具(iLoT)进行量化,并将结果与TensorFlow Lite的量化模型进行比较。在性能基准测试中,与初始的非量化模型相比,量化iLoT模型在英特尔硬件上的速度提高了1.73倍。通过不同的物理启发自开发的指标,我们验证了量化的iLoT模型与TensorFlow Lite模型相比,物理准确性损失更低。
英文摘要:
Deep learning is finding its way into high energy physics by replacing traditional Monte Carlo simulations. However, deep learning still requires an excessive amount of computational resources. A promising approach to make deep learning more efficient is to quantize the parameters of the neural networks to reduced precision. Reduced precision computing is extensively used in modern deep learning and results to lower execution inference time, smaller memory footprint and less memory bandwidth. In this paper we analyse the effects of low precision inference on a complex deep generative adversarial network model. The use case which we are addressing is calorimeter detector simulations of subatomic particle interactions in accelerator based high energy physics. We employ the novel Intel low precision optimization tool (iLoT) for quantization and compare the results to the quantized model from TensorFlow Lite. In the performance benchmark we gain a speed-up of 1.73x on Intel hardware for the quantized iLoT model compared to the initial, not quantized, model. With different physics-inspired self-developed metrics, we validate that the quantized iLoT model shows a lower loss of physical accuracy in comparison to the TensorFlow Lite model.
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。