Treffer: The impact of coding techniques on improving CNN image classification performance.

It has been observed that artificial neural networks require a significant amount of time and storage space. Because this is one of the most significant challenges that developers and users must overcome, it has been necessary to develop pre-trained models to use their results and reduce the time and storage space required for the training process. One example of this type of model is the acceptance model. In order to tackle the issues with storage and processing time, it has been suggested that a hybrid system consisting of acquisition models and lossless picture compression methods be constructed. Compared with the results of training the algorithm composed of integrating deep neural networks with Shannon Fano coding, the process of integrating Huffman coding with deep neural networks gave results with high accuracy (98.30%) with less training time (more than 100 seconds per training session). This contrasts the results of training the algorithm, which was composed of integrating deep neural networks with Shannon-Fano coding. [ABSTRACT FROM AUTHOR]

Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)