A new sequence optimization algorithm based on particle swarm for machine learning

Xie, Chao-Fan; Zhang, Fuquan

doi:10.1007/s12652-021-03004-3

Cited by 2 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First-order optimization algorithms (Xie and Zhang 2021 ), minimize an objective function parameterized by a model’s weight by updating the weights in the opposite direction of gradients of the objective function. When non-convex or non-differentiable functions are used, these methods may suffer from slow convergence and local minima issues.…”

Section: Related Workmentioning

confidence: 99%

“…Indeed, optimization methods can be divided into three categories Sun et al (2019); Zaheer and Shaziya (2019): i) first-order optimization methods such as stochastic gradient; ii) high-order optimization methods, mainly Newton's algorithm; and iii) heuristic / meta-heuristic derivative-free optimization methods. First-order optimization algorithms Xie and Zhang (2021), minimize an objective function parameterized by a model's weight by updating the weights in the opposite direction of gradients of the objective function. When nonconvex or non-differentiable functions are used, these methods may suffer from slow convergence and local minima issues.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Non-smooth Bayesian learning for artificial neural networks

Fakhfakh

Chaâri

Bouaziz

et al. 2022

J Ambient Intell Human Comput

View full text Add to dashboard Cite

Artificial neural networks (ANNs) are being widely used in supervised machine learning to analyze signals or images for many applications. Using an annotated learning database, one of the main challenges is to optimize the network weights. A lot of work on solving optimization problems or improving optimization methods in machine learning has been proposed successively such as gradient-based method, Newton-type method, meta-heuristic method. For the sake of efficiency, regularization is generally used. When non-smooth regularizers are used especially to promote sparse networks, such as the norm, this optimization becomes challenging due to non-differentiability issues of the target criterion. In this paper, we propose an MCMC-based optimization scheme formulated in a Bayesian framework. The proposed scheme solves the above-mentioned sparse optimization problem using an efficient sampling scheme and Hamiltonian dynamics. The designed optimizer is conducted on four (4) datasets, and the results are verified by a comparative study with two CNNs. Promising results show the usefulness of the proposed method to allow ANNs, even with low complexity levels, reaching high accuracy rates of up to . The proposed method is also faster and more robust concerning overfitting issues. More importantly, the training step of the proposed method is much faster than all competing algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Non-smooth Bayesian learning for artificial neural networks

Fakhfakh

Chaâri

Bouaziz

et al. 2022

J Ambient Intell Human Comput

View full text Add to dashboard Cite

show abstract

“…In recent years, advances in artificial intelligence (AI) and natural language processing (NLP) have led to the development of personalised learning platforms that can adapt to the needs and abilities of each student. These platforms use machine learning algorithms to analyse student performance data and provide personalised recommendations for reading materials and comprehension exercises (Xie et al, 2018). An example of a personalised learning platform for reading is Lexia Core5 Reading.…”

Section: Introductionmentioning

confidence: 99%

“…Recent advances in AI and NLP have shown promising results in addressing this challenge. Personalised learning platforms can provide a customised and adaptive approach to reading education that targets individual students' needs and abilities (Xie et al, 2018). Integrating AI into reading education offers a unique opportunity to improve reading proficiency among students, enabling them to access and comprehend increasingly complex texts, improve academic performance, and broaden their knowledge and intellectual horizons.…”

Section: Introductionmentioning

confidence: 99%

Effectiveness of AI-Based Personalised Reading Platforms in Enhancing Reading Comprehension

Hidayat

2024

JL4D

View full text Add to dashboard Cite

This study aimed at evaluating the effectiveness of microlearning in higher education. The sample consisted of first-year MBA students, and a post-test control group design was used to assess the effectiveness of a microlearning module. The results indicated that the use of microlearning was significantly related to learning performance and participants' reactions to the module. Moreover, the microlearning group scored significantly higher than the control group. The findings suggest that microlearning has the potential to improve learning outcomes and enhance participant engagement. However, the study has certain limitations, and future research is needed to gain a comprehensive understanding of the optimal design and delivery of microlearning modules. The study supports the use of microlearning in higher education as an effective instructional strategy.

show abstract

A new sequence optimization algorithm based on particle swarm for machine learning

Cited by 2 publications

References 16 publications

Non-smooth Bayesian learning for artificial neural networks

Non-smooth Bayesian learning for artificial neural networks

Effectiveness of AI-Based Personalised Reading Platforms in Enhancing Reading Comprehension

Contact Info

Product

Resources

About