Small sample prediction research based on optimized convolutional neural networks

Shaobo Chang; Xiaoyi Wang; Liang Chen

doi:10.1117/12.3006076

10 October 2023 Small sample prediction research based on optimized convolutional neural networks

Shaobo Chang, Xiaoyi Wang, Liang Chen

Proceedings Volume 12799, Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023); 127994M (2023) https://doi.org/10.1117/12.3006076
Event: 3rd International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), 2023, Kuala Lumpur, Malaysia

Abstract

The Wordle game was very popular after it was launched, attracting many players in the early stage. Under the rules of the game, the different characteristics of words may affect the distribution of scores in the different mode. The purpose of this report is to establish a model to study on the percentage distribution of attempts to submit reports. The innovation of this paper lies in the combination of convolutional neural network (CNN), bidirectional long and short term memory network (BiLSTM) and double attention mechanism (DA), and proposes a DCNN-BiLSTM network structure suitable for small sample prediction. Finally, a good prediction result is obtained.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Shaobo Chang, Xiaoyi Wang, and Liang Chen "Small sample prediction research based on optimized convolutional neural networks", Proc. SPIE 12799, Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), 127994M (10 October 2023); https://doi.org/10.1117/12.3006076

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available