A modified tunneling function method for non-smooth global optimization and its application in artificial neural network

Xu, Yuelei; Zhang, Ying; Wang, Shenggang

doi:10.1016/j.apm.2015.01.059

Cited by 16 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing research on tunneling and filled function is either on developing better auxiliary functions or extending to constrained and non-smooth optimization problems [27], [28], [29]. In general, these methods have similar drawbacks.…”

Section: B the Escaping Phasementioning

confidence: 99%

Learning to be Global Optimizer

Zhang,

Sun,

2020

Preprint

View full text Add to dashboard Cite

The advancement of artificial intelligence has cast a new light on the development of optimization algorithm. This paper proposes to learn a two-phase (including a minimization phase and an escaping phase) global optimization algorithm for smooth non-convex functions. For the minimization phase, a model-driven deep learning method is developed to learn the update rule of descent direction, which is formalized as a nonlinear combination of historical information, for convex functions. We prove that the resultant algorithm with the proposed adaptive direction guarantees convergence for convex functions. Empirical study shows that the learned algorithm significantly outperforms some well-known classical optimization algorithms, such as gradient descent, conjugate descent and BFGS, and performs well on ill-posed functions. The escaping phase from local optimum is modeled as a Markov decision process with a fixed escaping policy. We further propose to learn an optimal escaping policy by reinforcement learning. The effectiveness of the escaping policies is verified by optimizing synthesized functions and training a deep neural network for CIFAR image classification. The learned two-phase global optimization algorithm demonstrates a promising global search capability on some benchmark functions and machine learning tasks.

show abstract

Section: B the Escaping Phasementioning

confidence: 99%

Learning to be Global Optimizer

Zhang,

Sun,

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The calculation process is carried out repeatedly until the global minimum point is sought out. The tunneling algorithm provides a method to solve global optimization by the local optimization tool and shows great superiority in many applications of science subjects and engineering field [ 56 , 57 , 58 ].…”

Section: Modeling and Solving Of The Dynamic Reconstruction Modelmentioning

confidence: 99%

Dynamic Reconstruction Algorithm of Three-Dimensional Temperature Field Measurement by Acoustic Tomography

Shi

Inaki

2017

Sensors

View full text Add to dashboard Cite

Accuracy and speed of algorithms play an important role in the reconstruction of temperature field measurements by acoustic tomography. Existing algorithms are based on static models which only consider the measurement information. A dynamic model of three-dimensional temperature reconstruction by acoustic tomography is established in this paper. A dynamic algorithm is proposed considering both acoustic measurement information and the dynamic evolution information of the temperature field. An objective function is built which fuses measurement information and the space constraint of the temperature field with its dynamic evolution information. Robust estimation is used to extend the objective function. The method combines a tunneling algorithm and a local minimization technique to solve the objective function. Numerical simulations show that the image quality and noise immunity of the dynamic reconstruction algorithm are better when compared with static algorithms such as least square method, algebraic reconstruction technique and standard Tikhonov regularization algorithms. An effective method is provided for temperature field reconstruction by acoustic tomography.

show abstract

“…The variation in climatic conditions (i.e., seasonal and inter-annual changes) allows a wide spectrum of dynamic characteristics [14,15]. In addition, soils in which vegetation has been developed are also an important part to understand VIs response [16][17][18]. The analysis of these series can describe the vegetation dynamics driven by soil and climate characteristics.…”

Section: Introductionmentioning

confidence: 99%

Multiscaling NDVI Series Analysis of Rainfed Cereal in Central Spain

et al. 2021

View full text Add to dashboard Cite

Vegetation indices time series analysis is increasingly improved for characterizing agricultural land processes. However, this is challenging because of the multeity of factors affecting vegetation growth. In semiarid regions the rainfall, the soil properties and climate are strongly correlated with crop growth. These relationships are commonly analyzed using the normalized difference vegetation index (NDVI). NDVI series from two sites, belonging to different agroclimatic zones, were examined, decomposing them into the overall average pattern, residuals, and anomalies series. All of them were studied by applying the concept of the generalized Hurst exponent. This is derived from the generalized structure function, which characterizes the series’ scaling properties. The cycle pattern of NDVI series from both zones presented differences that could be explained by the differences in the climatic precipitation pattern and soil characteristics. The significant differences found in the soil reflectance bands confirm the differences in both sites. The scaling properties of NDVI original series were confirmed with Hurst exponents higher than 0.5 showing a persistent structure. The opposite was found when analyzing the residual and the anomaly series with a stronger anti-persistent character. These findings reveal the influences of soil–climate interactions in the dynamic of NDVI series of rainfed cereals in the semiarid.

show abstract

A modified tunneling function method for non-smooth global optimization and its application in artificial neural network

Cited by 16 publications

References 23 publications

Learning to be Global Optimizer

Learning to be Global Optimizer

Dynamic Reconstruction Algorithm of Three-Dimensional Temperature Field Measurement by Acoustic Tomography

Multiscaling NDVI Series Analysis of Rainfed Cereal in Central Spain

Contact Info

Product

Resources

About