arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.00540cs.LGcs.CVstat.ML
收藏

训练具有约束学习参数的深度神经网络

Training Deep Neural Networks with Constrained Learning Parameters

Rensselaer Polytechnic Institute(伦斯勒理工学院)

Prasanna Date, Christopher D. Carothers, John E. Mitchell, James A. Hendler, Malik Magdon-Ismail

摘要:

今天的深度学习模型主要在CPU和GPU上训练。虽然这些模型往往具有低误差,但由于双精度的浮点学习参数,它们消耗高功率并占用大量存储器。除了摩尔定律之外,很大一部分深度学习任务将在边缘计算系统上运行,这将成为整个计算结构不可或缺的一部分。随后,此类系统的训练深度学习模型必须经过定制和采用,以生成具有以下理想特性的模型:低错误、低内存和低功耗。我们相信,在类脑计算系统上运行的深度神经网络(DNN)(其中学习参数被约束为具有一组有限的离散值)将有助于具有这些理想特性的智能边缘计算系统。为此,我们提出了组合神经网络训练算法(CoNNTrA),该算法利用基于坐标梯度下降的方法来训练具有有限离散学习参数的深度学习模型。接下来,我们详细阐述了理论基础,并评估的计算复杂性的CoNNTrA。作为概念证明,我们使用CoNNTrA在MNIST、Iris和ImageNet数据集上使用三元学习参数训练深度学习模型,并将其性能与使用反向传播训练的相同模型进行比较。我们使用以下性能指标进行比较:(i)训练错误;(ii)验证错误;(iii)内存使用;以及(iv)训练时间。我们的研究结果表明,CoNNTrA模型使用的内存少32倍,误差与反向传播模型相当。

英文摘要:

Today's deep learning models are primarily trained on CPUs and GPUs. Although these models tend to have low error, they consume high power and utilize large amount of memory owing to double precision floating point learning parameters. Beyond the Moore's law, a significant portion of deep learning tasks would run on edge computing systems, which will form an indispensable part of the entire computation fabric. Subsequently, training deep learning models for such systems will have to be tailored and adopted to generate models that have the following desirable characteristics: low error, low memory, and low power. We believe that deep neural networks (DNNs), where learning parameters are constrained to have a set of finite discrete values, running on neuromorphic computing systems would be instrumental for intelligent edge computing systems having these desirable characteristics. To this extent, we propose the Combinatorial Neural Network Training Algorithm (CoNNTrA), that leverages a coordinate gradient descent-based approach for training deep learning models with finite discrete learning parameters. Next, we elaborate on the theoretical underpinnings and evaluate the computational complexity of CoNNTrA. As a proof of concept, we use CoNNTrA to train deep learning models with ternary learning parameters on the MNIST, Iris and ImageNet data sets and compare their performance to the same models trained using Backpropagation. We use following performance metrics for the comparison: (i) Training error; (ii) Validation error; (iii) Memory usage; and (iv) Training time. Our results indicate that CoNNTrA models use 32x less memory and have errors at par with the Backpropagation models.

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。

↑