Improved Recurrent Neural Networks for Text Classification and Dynamic Sylvester Equation Solving

Chen, Weijie; Gerontitis, Dimitrios; Qiu, Lixin; Zhu, Jingcan

doi:10.1007/s11063-023-11176-6

Cited by 7 publications

(4 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The tests based on average text length, number of subject areas, and using related and non-related subject areas in test groups. In average 28-34 tests per group were using all five different number of subject areas (4,6,10,14,20) and each test has his own pair with using nonrelated subject areas. Totally was created 12 test groups.…”

Section: Methodsmentioning

confidence: 99%

“…Similar calculations were found in sphere of security for cryptosystems, which also use adjacency metrics for preventing side channels attacks [9]. Subsequently, this matrix is sent to a recurrent neural network, which returns a vector of values for each of the streams, which determines the level of contiguity of the subject area with the user's request [4]. As a result of the search in each of the subject areas, the streams form a list of the most relevant data in the form of a list of terms with a coefficient of adjacency to the user's request.…”

Section: Fig 6 Chatbot Client-server Architecturementioning

confidence: 95%

See 1 more Smart Citation

Tworzenie Wysoce Wyspecjalizowanych Chatbotów Do Zaawansowanego Wyszukiwania

Yarovyi,

Kudriavtsev

2024

IAPGOS

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Fig 6 Chatbot Client-server Architecturementioning

confidence: 95%

Tworzenie Wysoce Wyspecjalizowanych Chatbotów Do Zaawansowanego Wyszukiwania

Yarovyi,

Kudriavtsev

2024

IAPGOS

View full text Add to dashboard Cite

show abstract

“…Similar models are used in [33,34,35]. The authors in [36] propose enhancing RNN models by modifying the activation functions used.…”

Section: Related Workmentioning

confidence: 99%

Improving Scientific Literature Classification: A Parameter-Efficient Transformer-Based Approach

Munzir Ahanger,

Arif Wani

2023

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

Transformer-based models have been utilized in natural language processing (NLP) for a wide variety of tasks like summarization, translation, and conversational agents. These models can capture long-term dependencies within the input, so they have significantly more representational capabilities than Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). Nevertheless, these models require significant computational resources in terms of high memory usage, and extensive training time. In this paper, we propose a novel document categorization model, with improved parameter efficiency that encodes text using a single, lightweight, multiheaded attention encoder block. The model also uses a hybrid word and position embedding to represent input tokens. The proposed model is evaluated for the Scientific Literature Classification task (SLC) and is compared with state-of-the-art models that have previously been applied to the task. Ten datasets of varying sizes and class distributions have been employed in the experiments. The proposed model shows significant performance improvements, with a high level of efficiency in terms of parameter and computation resource requirements as compared to other transformer-based models, and outperforms previously used methods.

show abstract

“…Recently, some researchers have also proposed robust and noise-tolerant ZNN models with applications to dynamic complex matrix equation solving [21,22] and mobile manipulator path tracking [23,24]. Additionally, improved recurrent neural networks have been proposed for text classification and dynamic Sylvester equation solving [25].…”

Section: Introductionmentioning

confidence: 99%

An Adaptive Zeroing Neural Network with Non-Convex Activation for Time-Varying Quadratic Minimization

et al. 2023

View full text Add to dashboard Cite

The field of position tracking control and communication engineering has been increasingly interested in time-varying quadratic minimization (TVQM). While traditional zeroing neural network (ZNN) models have been effective in solving TVQM problems, they have limitations in adapting their convergence rate to the commonly used convex activation function. To address this issue, we propose an adaptive non-convex activation zeroing neural network (AZNNNA) model in this paper. Using the Lyapunov theory, we theoretically analyze the global convergence and noise-immune characteristics of the proposed AZNNNA model under both noise-free and noise-perturbed scenarios. We also provide computer simulations to illustrate the effectiveness and superiority of the proposed model. Compared to existing ZNN models, our proposed AZNNNA model outperforms them in terms of efficiency, accuracy, and robustness. This has been demonstrated in the simulation experiment of this article.

show abstract

Improved Recurrent Neural Networks for Text Classification and Dynamic Sylvester Equation Solving

Cited by 7 publications

References 47 publications

Tworzenie Wysoce Wyspecjalizowanych Chatbotów Do Zaawansowanego Wyszukiwania

Tworzenie Wysoce Wyspecjalizowanych Chatbotów Do Zaawansowanego Wyszukiwania

Improving Scientific Literature Classification: A Parameter-Efficient Transformer-Based Approach

An Adaptive Zeroing Neural Network with Non-Convex Activation for Time-Varying Quadratic Minimization

Contact Info

Product

Resources

About