Probabilistic Constrained Optimization for Predictive Video Streaming by Deep Learning

Yin, Manru; Sun, Chengjian; Yang, Chenyang; Han, Shengqian

doi:10.1109/tcomm.2022.3227932

Cited by 1 publication

(1 citation statement)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In systematic research regarding the dissection and reconstruction of neural network model internal structures, split learning has emerged as a recent focus. Tese techniques involve disassembling all-in-one neural network models into several modules, each possessing varying degrees of independence [28][29][30][31]. Tese split modules can operate on diferent computing devices and communicate with each other via data links.…”

Section: Related Workmentioning

confidence: 99%

Semi-White-Box Strategy: Enhancing Data Efficiency and Interpretability of Convolutional Neural Networks in Image Processing

Wang,

Zeng,

Qin

et al. 2023

International Journal of Intelligent Systems

View full text Add to dashboard Cite

Data-hunger is a persistent challenge in machine learning, particularly in the field of image processing based on convolutional neural networks (CNNs). This study systematically investigates the factors contributing to data-hunger in machine-learning-based image-processing algorithms. The results revealed that the proliferation of model parameters, the lack of interpretability, and the complexity of model structure are significant factors influencing data-hunger. Based on these findings, this paper introduces a novel semi-white-box neural network model construction strategy. This approach effectively reduces the number of model parameters while enhancing the interpretability of model components. It accomplishes this by constraining uninterpretable processes within the model and leveraging prior knowledge of image processing for model. Rather than relying on a single all-in-one model, a semi-white-box model is composed of multiple smaller models, each responsible for extracting fundamental semantic features. The final output is derived from these features and prior knowledge. The proposed strategy holds the potential to substantially decrease data requirements under specific data source conditions while improving the interpretability of model components. Validation experiments are conducted on well-established datasets, including MNIST, Fashion MNIST, CIFAR, and generated data. The results demonstrate the superiority of the semi-white-box strategy over the traditional all-in-one approach in terms of accuracy when trained with equivalent data volumes. Impressively, on the tested datasets, a simplified semi-white-box model achieves performance close to that of ResNet while utilizing a small number of parameters. Furthermore, the semi-white-box strategy offers improved interpretability and parameter reusability features that are challenging to achieve with the all-in-one approach. In conclusion, this paper contributes to mitigating data-hunger challenges in machine-learning-based image processing through the introduction of a novel semi-white-box model construction strategy, backed by empirical evidence of its effectiveness.

show abstract

Section: Related Workmentioning

confidence: 99%