Incremental learning paradigm with privileged information for random vector functional-link networks: IRVFL+

Dai, Wei; Ao, Yanshuang; Zhou, Linna; Zhou, Ping; Wang, Xuesong

doi:10.1007/s00521-021-06793-y

Cited by 10 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SSO algorithm improves the parameters of the standard RVFL model. Dai et al [78] incorporated LUPI paradigm into incremental RVFL (IRVFL) model and proposed IRVFL+ that has strong theoretical foundation. IRVFL+ model has been trained via two approaches.…”

Section: Rvfl With Bayesian Inference (Bi) and Other Techniquesmentioning

confidence: 99%

“…Then, a grid search is conducted to select the hyperparameters, number of hidden nodes, and regularization strength, according to the forecasting errors on the validation set. Choosing the optimal activation function and number of hidden neurons is also an challenging job so some researchers adopt incremental learning techniques [78] and kernel trick [28] to avoid these issues. Table 1 shows the list of activation functions used in the literature.…”

Section: Hyper-parameters Optimization For Single-layer Rvflmentioning

confidence: 99%

See 1 more Smart Citation

Random vector functional link network: recent developments, applications, and future directions

Malik¹,

Gao²,

Ganaie³

et al. 2022

Preprint

View full text Add to dashboard Cite

Neural networks have been successfully employed in various domain such as classification, regression and clustering, etc. Generally, the back propagation (BP) based iterative approaches are used to train the neural networks, however, it results in the issues of local minima, sensitivity to learning rate and slow convergence. To overcome these issues, randomization based neural networks such as random vector functional link (RVFL) network have been proposed. RVFL model has several characteristics such as fast training speed, simple architecture, and universal approximation capability, that make it a viable randomized neural network. This article presents the comprehensive review of the development of RVFL model, which can serve as the extensive summary for the beginners as well as practitioners. We discuss the shallow RVFL, ensemble RVFL, deep RVFL and ensemble deep RVFL models. The variations, improvements and applications of RVFL models are discussed in detail. Moreover, we discuss the different hyperparameter optimization techniques followed in the literature to improve the generalization performance of the RVFL model. Finally, we give potential future research directions/opportunities that can inspire the researchers to improve the RVFL architecture further.

show abstract

Section: Rvfl With Bayesian Inference (Bi) and Other Techniquesmentioning

confidence: 99%

Section: Hyper-parameters Optimization For Single-layer Rvflmentioning

confidence: 99%

Random vector functional link network: recent developments, applications, and future directions

Malik¹,

Gao²,

Ganaie³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Another approach by Alalimi et al (2021) involved employing the Spherical Search Optimizer (SSO) algorithm to optimize the RVFL model, thereby creating the SSO-RVFL model. Dai et al (2022) incorporated the LUPI paradigm into the incremental RVFL (IRVFL) model to propose IRVFL+ that has a strong theoretical foundation. The RVFL-EO model incorporates the equilibrium optimizer (EO) algorithm, was proposed by Abd Elaziz et al (2021).…”

Section: Other Rvfl Network Variants and Applicationsmentioning

confidence: 99%

From noise to information: discriminative tasks based on randomized neural networks and generative tasks based on diffusion models

View full text Add to dashboard Cite

In this thesis, I delve into the realm of noise and information, exploring the application and capabilities of randomized neural networks in discriminative tasks, as well as the utilization of diffusion models in generative tasks. I begin by investigating the inherent randomness in neural networks, and how this randomness can be harnessed to perform discriminative tasks with high accuracy. I then transition to the domain of generative tasks, where I employ diffusion models to generate high-quality data from noise. The primary innovations include:

show abstract

Grafting constructive algorithm in feedforward neural network learning

Zhang

Xie

2022

Appl Intell

View full text Add to dashboard Cite

Incremental learning paradigm with privileged information for random vector functional-link networks: IRVFL+

Cited by 10 publications

References 32 publications

Random vector functional link network: recent developments, applications, and future directions

Random vector functional link network: recent developments, applications, and future directions

From noise to information: discriminative tasks based on randomized neural networks and generative tasks based on diffusion models

Grafting constructive algorithm in feedforward neural network learning

Contact Info

Product

Resources

About