The implementation of renewable energy brings numerous advantages including reduction of power transmission cost and minimization of the global warming problems. The investigation of the influencing ...operational parameters as well as optimization of the solar energy system is the key factors to enhance the power conversion efficiency. The different optimization methods in solar energy applications have been utilized to improve performance efficiency. However, the development of optimal methods under the intermittent nature of solar energy resources remains key issues to be explored. Therefore, this paper presents a comprehensive review of the main generic objectives of optimization in renewable energy systems, such as solar energy systems. Moreover, this study introduces the most recent intelligent optimization methods used in solar energy systems with regard to its functions, constraints, research gaps and contributions. From this review, it can be concluded that the main objectives of optimizations methods are to reduce minimize investment, operation and maintenance costs and emissions to enhance the system reliability. This review also outlines a brief discussion of various challenges and issues of solar energy optimization. Finally, the review delivers some effective future directions toward the development of an efficient and stable solar PV system.
•A comprehensive review on the optimization objectives in solar energy systems are explained.•Intelligent control strategies and optimization methods are utilized in solar energy systems.•Optimizations strategies reduce emissions and costs of system into maximizing reliability.•Solar energy systems enhance the output power and minimize the interruptions in the connected load.•This review highlights the challenges on optimization to increase efficient and stable PV system.
The Taguchi optimization method is an efficient method for motor design optimization. However, it is hard to handle the multiobjective motor optimization problem with big design space for the ...parameters. To deal with this problem, in this article, a fuzzy method and sequential Taguchi method to optimize an inter permanent magnet synchronous motor (IPMSM) is employed. The fuzzy inference system is introduced to convert the multiple objectives to a single-objective optimization problem. The sequential Taguchi method is used to optimize the structural parameters at multiple levels to improve the accuracy of optimization. After the optimal selection analysis, the best combination of motor structure factors is obtained. By comparing the optimization result of the proposed method with that of the conventional Taguchi optimization method, the effectiveness and superiority of the proposed method are verified.
We introduce an end-to-end deep-learning framework for 3D medical image registration. In contrast to existing approaches, our framework combines two registration methods: an affine registration and a ...vector momentum-parameterized stationary velocity field (vSVF) model. Specifically, it consists of three stages. In the first stage, a multi-step affine network predicts affine transform parameters. In the second stage, we use a U-Net-like network to generate a momentum, from which a velocity field can be computed via smoothing. Finally, in the third stage, we employ a self-iterable map-based vSVF component to provide a non-parametric refinement based on the current estimate of the transformation map. Once the model is trained, a registration is completed in one forward pass. To evaluate the performance, we conducted longitudinal and cross-subject experiments on 3D magnetic resonance images (MRI) of the knee of the Osteoarthritis Initiative (OAI) dataset. Results show that our framework achieves comparable performance to state-of-the-art medical image registration approaches, but it is much faster, with a better control of transformation regularity including the ability to produce approximately symmetric transformations, and combining affine as well as non-parametric registration.
Machine learning develops rapidly, which has made many theoretical breakthroughs and is widely applied in various fields. Optimization, as an important part of machine learning, has attracted much ...attention of researchers. With the exponential growth of data amount and the increase of model complexity, optimization methods in machine learning face more and more challenges. A lot of work on solving optimization problems or improving optimization methods in machine learning has been proposed successively. The systematic retrospect and summary of the optimization methods from the perspective of machine learning are of great significance, which can offer guidance for both developments of optimization and machine learning research. In this article, we first describe the optimization problems in machine learning. Then, we introduce the principles and progresses of commonly used optimization methods. Finally, we explore and give some challenges and open problems for the optimization in machine learning.
Transfer learning, which allows a source task to affect the inductive bias of the target task, is widely used in computer vision. The typical way of conducting transfer learning with deep neural ...networks is to fine-tune a model pretrained on the source task using data from the target task. In this paper, we propose an adaptive fine-tuning approach, called SpotTune, which finds the optimal fine-tuning strategy per instance for the target data. In SpotTune, given an image from the target task, a policy network is used to make routing decisions on whether to pass the image through the fine-tuned layers or the pre-trained layers. We conduct extensive experiments to demonstrate the effectiveness of the proposed approach. Our method outperforms the traditional fine-tuning approach on 12 out of 14 standard datasets. We also compare SpotTune with other state-of-the-art fine-tuning strategies, showing superior performance. On the Visual Decathlon datasets, our method achieves the highest score across the board without bells and whistles.
We propose a novel regularization algorithm to train deep neural networks, in which data at training time is severely biased. Since a neural network efficiently learns data distribution, a network is ...likely to learn the bias information to categorize input data. It leads to poor performance at test time, if the bias is, in fact, irrelevant to the categorization. In this paper, we formulate a regularization loss based on mutual information between feature embedding and bias. Based on the idea of minimizing this mutual information, we propose an iterative algorithm to unlearn the bias information. We employ an additional network to predict the bias distribution and train the network adversarially against the feature embedding network. At the end of learning, the bias prediction network is not able to predict the bias not because it is poorly trained, but because the feature embedding network successfully unlearns the bias information. We also demonstrate quantitative and qualitative experimental results which show that our algorithm effectively removes the bias information from feature embedding.
Plenoxels: Radiance Fields without Neural Networks Fridovich-Keil, Sara; Yu, Alex; Tancik, Matthew ...
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),
2022-June
Conference Proceeding
Odprti dostop
We introduce Plenoxels (plenoptic voxels), a systemfor photorealistic view synthesis. Plenoxels represent a scene as a sparse 3D grid with spherical harmonics. This representation can be optimized ...from calibrated images via gradient methods and regularization without any neural components. On standard, benchmark tasks, Plenoxels are optimized two orders of magnitude faster than Neural Radiance Fields with no loss in visual quality. For video and code, please see https://alexyu.net/plenoxels.
Generating 3D Adversarial Point Clouds Xiang, Chong; Qi, Charles R.; Li, Bo
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),
2019-June
Conference Proceeding
Odprti dostop
Deep neural networks are known to be vulnerable to adversarial examples which are carefully crafted instances to cause the models to make wrong predictions. While adversarial examples for 2D images ...and CNNs have been extensively studied, less attention has been paid to 3D data such as point clouds. Given many safety-critical 3D applications such as autonomous driving, it is important to study how adversarial point clouds could affect current deep 3D models. In this work, we propose several novel algorithms to craft adversarial point clouds against PointNet, a widely used deep neural network for point cloud processing. Our algorithms work in two ways: adversarial point perturbation and adversarial point generation. For point perturbation, we shift existing points negligibly. For point generation, we generate either a set of independent and scattered points or a small number (1-3) of point clusters with meaningful shapes such as balls and airplanes which could be hidden in the human psyche. In addition, we formulate six perturbation measurement metrics tailored to the attacks in point clouds and conduct extensive experiments to evaluate the proposed algorithms on the ModelNet40 3D shape classification dataset. Overall, our attack algorithms achieve a success rate higher than 99% for all targeted attacks.
Truncated Newton full waveform inversion is an attractive alternative to conventional gradient-based optimization algorithms. This method accounts for the Hessian within the inversion; however, it ...is implemented in a "Hessian-free" fashion, without explicit calculation or storage of the Hessian matrix. At each iteration, we obtain the search direction through a conjugate-gradient (CG) solution of the Newton linear system, which requires only evaluations of Hessian-vector products. Due to the additional cost associated with inner CG iterations, it is indispensable to apply a preconditioning strategy on the CG algorithm to improve its convergence, reducing the number of CG iterations. In this work, we study two preconditioned CG schemes. We propose a scheme based on model reparameterization that adopts a preconditioner operator that combines smoothness and the illumination compensation effect of the pseudo-Hessian. We also investigate a more conventional preconditioning scheme that uses only the pseudo-Hessian preconditioner. The numerical experiments show that preconditioning using model reparameterization, which combines pseudo-Hessian compensation with smoothing, outperforms the more conventional preconditioning scheme that exclusively uses the pseudo-Hessian operator.
We present a novel approach to view synthesis using multiplane images (MPIs). Building on recent advances in learned gradient descent, our algorithm generates an MPI from a set of sparse camera ...viewpoints. The resulting method incorporates occlusion reasoning, improving performance on challenging scene features such as object boundaries, lighting reflections, thin structures, and scenes with high depth complexity. We show that our method achieves high-quality, state-of-the-art results on two datasets: the Kalantari light field dataset, and a new camera array dataset, Spaces, which we make publicly available.