Convolutional neural networks (CNNs) play an important role in image recognition applications. Fast training of image recognition systems is a crucial point, because the system should be trained for each new image class. These networks are trained using lengthy calculations. Focus of engineering is on obtaining a fast, but stable optimisation method. Momentum technique which is used in backpropagation algorithms is like a proportional–integral (PI) controller that is widely employed in automatic control systems. It takes the integral of past errors and helps reaching the training targets. Proportional + momentum + derivative (ProMoD) method adds gradient of update matrices to the training process and builds an optimiser such as the widely used PI–derivative controller. The method accelerates the movement toward the target accuracy levels. This is achieved by doing bigger corrections in the beginning using the differences in the calculated update matrices. In this research, ProMoD method is tested on image recognition applications and CNNs. Modified national institute of standards and technology database (MNIST) and Fashion-MNIST datasets are used for evaluating the performance. Experimental results showed that ProMoD might perform much faster in training of CNNs and consume proportionally less power with respect to the momentum and stochastic gradient descent (SGD) techniques.

中文翻译：

---

使用ProMoD反向传播算法加速卷积神经网络训练

卷积神经网络（CNN）在图像识别应用中起着重要作用。图像识别系统的快速培训至关重要，因为应该针对每个新的图像类别对系统进行培训。使用冗长的计算来训练这些网络。工程的重点是获得快速但稳定的优化方法。反向传播算法中使用的动量技术类似于比例积分（PI）控制器，该控制器广泛应用于自动控制系统中。它整合了过去的错误，有助于达到培训目标。比例+动量+导数（ProMoD）方法在训练过程中增加了更新矩阵的梯度，并建立了诸如广泛使用的PI导数控制器之类的优化器。该方法加速了向目标精度水平的移动。这是通过在开始时使用计算出的更新矩阵中的差异进行较大的校正来实现的。在这项研究中，ProMoD方法在图像识别应用程序和CNN上进行了测试。修改后的国家标准与技术研究院（MNIST）和Fashion-MNIST数据集用于评估性能。实验结果表明，相对于动量和随机梯度下降（SGD）技术，ProMoD在训练CNN时可能执行得更快，并且所消耗的功率也成比例地减少。修改后的国家标准与技术研究院（MNIST）和Fashion-MNIST数据集用于评估性能。实验结果表明，就动量和随机梯度下降（SGD）技术而言，ProMoD在CNN的训练中可能执行得更快，并且所消耗的功率也成比例地减少。修改后的国家标准与技术研究院（MNIST）和Fashion-MNIST数据集用于评估性能。实验结果表明，相对于动量和随机梯度下降（SGD）技术，ProMoD在训练CNN时可能执行得更快，并且所消耗的功率也成比例地减少。