Impact of Autotuned Fully Connected Layers on Performance of Self-supervised Models for Image Classification

With the recent advancements of deep learning-based methods in image classification,the requirement of a huge amount of training data is inevitable to avoid overfitting problems.Moreover,supervised deep learning models require labelled datasets for train-ing.Preparing such a huge amount of labelled data requires considerable human effort and time.In this scenario,self-supervised models are becoming popular because of their ability to learn even from unlabelled datasets.However,the efficient transfer of knowledge learned by self-supervised models into a target task,is an unsolved problem.This paper proposes a method for the efficient transfer of know-ledge learned by a self-supervised model,into a target task.Hyperparameters such as the number of layers,the number of units in each layer,learning rate,and dropout are automatically tuned in these fully connected(FC)layers using a Bayesian optimization technique called the tree-structured parzen estimator(TPE)approach algorithm.To evaluate the performance of the proposed method,state-of-the-art self-supervised models such as SimClr and SWAV are used to extract the learned features.Experiments are carried out on the CIFAR-10,CIFAR-100,and Tiny ImageNet datasets.The proposed method outperforms the baseline approach with margins of 2.97%,2.45%,and 0.91%for the CIFAR-100,Tiny ImageNet,and CIFAR-10 datasets,respectively.

9FA燃气轮机DLN2.6+燃烧系统环保经济效益分析

9FA燃气轮机目前大部分使用的是DLN2.0燃烧系统,由于其燃烧模式和控制系统的原因造成运行过程中瞬时出现烟气的氮氧化物排放浓度超出国家环保局制定的排放标准;另外由于在燃烧模式切换的过程中和极端天气下,由于燃烧脉动或其他不确定因素,导致出现燃烧室损坏的问题,增加了运行风险和检修成本。本文通过对9FA燃气轮机排放烟气的氨氧化物浓度高产生的原因、燃烧脉动升高的原因以及最新的DLN2.6+燃烧器和Op Flex Auto Tune自动燃烧调整系统的工作原理,分析其环保经济效益。

Relay Feedback Based Autotuning PID Control of Paper Basis Weight in Paper Making Process

The brief arts and crafts of the ordinary fourdrinier are introduced first. After the intractable points of paper basis weight (BW) control are analyzed, an autotuning PID/PI control algorithm based on relay feedback identification is proposed, which has such advantages as simple parameter adjustment, little dependence on process model, strong robustness and easiness to implementation. And it is very suitable for controlling such processes as BW loop with large time delay.

Performance Improvement of Distributed Systems by Autotuning of the Configuration Parameters

The performance of distributed computing systems is partially dependent on configuration parameters recorded in configuration files. Evolutionary strategies, with their ability to have a global view of the structural information, have been shown to effectively improve performance. However, most of these methods consume too much measurement time. This paper introduces an ordinal optimization based strategy combined with a back propagation neural network for autotuning of the configuration parameters. The strat- egy was first proposed in the automation community for complex manufacturing system optimization and is customized here for improving distributed system performance. The method is compared with the covariance matrix algorithm. Tests using a real distributed system with three-tier servers show that the strategy reduces the testing time by 40% on average at a reasonable performance cost.