New studies on dynamic analysis of asymptotically almost periodic recurrent neural networks involving mixed delays

Humans are increasingly integrated with devices that enable the collection of vast unstructured opinionated data. Accurately analysing subjective information from this data is the task of sentiment analysis (an actively researched area in NLP). Deep learning provides a diverse selection of architectures to model sentiment analysis tasks and has surpassed other machine learning methods as the foremast approach for performing sentiment analysis tasks. Recent developments in deep learning architectures represent a shift away from Recurrent and Convolutional neural networks and the increasing adoption of Transformer language models. Utilising pre-trained Transformer language models to transfer knowledge to downstream tasks has been a breakthrough in NLP. This survey applies a task-oriented taxonomy to recent trends in architectures with a focus on the theory, design and implementation. To the best of our knowledge, this is the only survey to cover state-of-the-art Transformer-based language models and their performance on the most widely used benchmark datasets. This survey paper provides a discussion of the open challenges in NLP and sentiment analysis. The survey covers five years from 1st Jul 2017 to 1st Jul 2022.

show abstract

Anti-periodic synchronization of quaternion-valued high-order Hopfield neural networks with delays

Gao

Dai

2022

MATH

View full text Add to dashboard Cite

<abstract><p>This paper proposes a class of quaternion-valued high-order Hopfield neural networks with delays. By using the non-decomposition method, non-reduced order method, analytical techniques in uniform convergence functions sequence, and constructing Lyapunov function, we obtain several sufficient conditions for the existence and global exponential synchronization of anti-periodic solutions for delayed quaternion-valued high-order Hopfield neural networks. Finally, an example and its numerical simulations are given to support the proposed approach. Our results play an important role in designing inertial neural networks.</p></abstract>

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

New studies on dynamic analysis of asymptotically almost periodic recurrent neural networks involving mixed delays

Cited by 3 publications

References 36 publications

Positive almost periodicity on a n -species food chain system incorporating time-varying delays and polluted environments

Positive almost periodicity on a n -species food chain system incorporating time-varying delays and polluted environments

Deep Learning in Sentiment Analysis: Recent Architectures

Anti-periodic synchronization of quaternion-valued high-order Hopfield neural networks with delays

Contact Info

Product

Resources

About