Neural Architecture Search for Portrait Parsing

Lyu, Bo; Yang, Yin; Wen, Shiping; Huang, Tingwen; Li, Ké

doi:10.1109/tnnls.2021.3104872

Cited by 10 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Things become even more challenging when the constraints are (partially) unobservable [80,81]. It is also worth noting that evolutionary computation and multi-objective optimization have been successfully applied to solve real-world problems, e.g., natural language processing [82], neural architecture search [83][84][85][86], robustness of neural networks [87][88][89][90][91][92], software engineering [93][94][95][96][97], smart grid management [2,98,99], communication networks [100][101][102][103], machine learning [104][105][106][107][108], and visualization [109]. Finally, the explainability of the policies of interest and their implications has rarely been discussed in the literature, representing another area for future investigation.…”

Section: Discussionmentioning

confidence: 99%

An Improved Multi-objective Optimization Algorithm Based on Reinforcement Learning

Liu

Zhou

Qiu

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Multi-objective reinforcement learning (MORL) aims to find a set of high-performing and diverse policies that address trade-offs between multiple conflicting objectives. However, in practice, decision makers (DMs) often deploy only one or a limited number of trade-off policies. Providing too many diversified trade-off policies to the DM not only significantly increases their workload but also introduces noise in multi-criterion decision-making. With this in mind, we propose a humanin-the-loop policy optimization framework for preference-based MORL that interactively identifies policies of interest. Our method proactively learns the DM's implicit preference information without requiring any a priori knowledge, which is often unavailable in real-world black-box decision scenarios. The learned preference information is used to progressively guide policy optimization towards policies of interest. We evaluate our approach against three conventional MORL algorithms that do not consider preference information and four state-of-the-art preference-based MORL algorithms on two MORL environments for robot control and smart grid management. Experimental results fully demonstrate the effectiveness of our proposed method in comparison to the other peer algorithms.

show abstract

Section: Discussionmentioning

confidence: 99%

An Improved Multi-objective Optimization Algorithm Based on Reinforcement Learning

Liu

Zhou

Qiu

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Following the construction of the VNoE solution, the corresponding optimal VLiE solution and FS allocation are obtained in the lower-level optimization, which will be discussed in Section 3.4. The performance of a completed solution comprised of the VNoE and VLiE results can then be evaluated [54][55][56][57][58]. The fitness function is the cost for fulfilling the total resource requirements of both VNoE and VLiE, and it is calculated as follows…”

Section: Fitness Evaluationmentioning

confidence: 99%

Multidimensional Resource Fragmentation-Aware Virtual Network Embedding in MEC Systems Interconnected by Metro Optical Networks

Guan¹,

Song²,

Qi³

et al. 2023

Preprint

View full text Add to dashboard Cite

The increasing demand for diverse emerging applications has resulted in the interconnection of multi-access edge computing (MEC) systems via metro optical networks. To cater to these diverse applications, network slicing has become a popular tool for creating specialized virtual networks. However, resource fragmentation caused by uneven utilization of multidimensional resources can lead to reduced utilization of limited edge resources. To tackle this issue, this paper focuses on addressing the multidimensional resource fragmentation problem in virtual network embedding (VNE) in MEC systems with the aim of maximizing the profit of an infrastructure provider (InP). The VNE problem in MEC systems is transformed into a bilevel optimization problem, taking into account the interdependence between virtual node embedding (VNoE) and virtual link embedding (VLiE). To solve this problem, we propose a nested bilevel optimization approach named BiVNE. The VNoE is solved using the ant colony system (ACS) in the upper level, while the VLiE is solved using a combination of a shortest path algorithm and an exact-fit spectrum slot allocation method in the lower level. Evaluation results show that the BiVNE algorithm can effectively enhance the profit of the InP by increasing the acceptance ratio and avoiding resource fragmentation simultaneously.

show abstract

“…The methods and comparison methods used in this paper. Such as generalized regression neural network (GRNN) model, short‐term memory neural network LSTM, 23 support vector regression SVR, 24 cyclic neural network RNN, 25 RNN‐CNN neural network fusion algorithm, 26 generative adversarial networks (GAN) 27 Neural Architecture Search (NAS) 28 and other modern intelligent algorithms, are some of the most commonly used forecasting methods. These methods are based on more perfect theoretical knowledge and more developed science and technology innovation.…”

Section: Introductionmentioning

confidence: 99%

Short‐term load forecasting based on a generalized regression neural network optimized by an improved sparrow search algorithm using the empirical wavelet decomposition method

Fan¹,

Li²,

Zhang³

et al. 2023

Energy Science & Engineering

View full text Add to dashboard Cite

With the development of the electric market, electric load forecasting has been increasingly pursued by many scholars. Because the electric load is affected by many factors, it is characterized by volatility and uncertainty, and it cannot be forecasted accurately only by a single model. In the research, a short‐term load forecasting integrated model is proposed to solve the problem of inaccurate forecasting of a single model. The key point of using the integrated model to forecast is to optimize the decomposed sequence to improve the accuracy of the forecast. empirical wavelet decomposition (EWT) is used to decompose the sequence into stationary sequences and avoid modal aliasing; the sparrow search algorithm (SSA) simulates the forecasting and anti‐forecasting behavior of the sparrow population, which is very similar to the electricity consumption behavior of various industries and has good optimization effect; generalized regression neural network (GRNN) is used for forecast and reconstruction; This is the EWT‐SSA‐GRNN model. This paper studies and analyzes the power load of a city in southern Australia. The results show that the integrated model reduces volatility through decomposition and optimization, and can improve forecast accuracy.

show abstract

Neural Architecture Search for Portrait Parsing

Cited by 10 publications

References 35 publications

An Improved Multi-objective Optimization Algorithm Based on Reinforcement Learning

An Improved Multi-objective Optimization Algorithm Based on Reinforcement Learning

Multidimensional Resource Fragmentation-Aware Virtual Network Embedding in MEC Systems Interconnected by Metro Optical Networks

Short‐term load forecasting based on a generalized regression neural network optimized by an improved sparrow search algorithm using the empirical wavelet decomposition method

Contact Info

Product

Resources

About