Comprehensive Analysis of Network Depth and Numerical Precision on MNIST Classification:Training Dynamics and Deployment Efficiency
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Today’s deep learning field is developing rapidly, and its focus is no longer limited to pursuing the ultimate accuracy of models on large servers, but paying more and more attention to how to improve model efficiency in order to deploy it to edge devices. In this study, we focus on how adjusting the two key knobs of network depth and numerical precision affects the performance of neural networks. We used the classic MNIST dataset as a test benchmark to examine fully connected neural networks with depths ranging from 2 to 10 layers.In the experimental part, we compared traditional FP32 training with FP16 mixed-precision training, and further studied the impact of introducing INT8 dynamic quantization after training. The results show that FP16 mixed-precision training is very effective: compared with the FP32 model, its accuracy loss is minimal (usually less than 0.2%) and can benefit from hardware acceleration. At the same time, in the simulated deployment experiment, we found that INT8 dynamic quantization can greatly reduce the model size by about 70–75%, while the decrease in accuracy is very limited (only about 0.5–1.2%). This result confirms our conjecture: in resource-constrained environments such as Internet of Things devices or mobile processors, reducing numerical precision is not only practical, but also an efficient means for large-scale applications.
Fields of Study & Subjects
Advanced Neural Network Applications
Numerical Methods and Algorithms
Machine Learning and Data Classification
Publication details
- Journal / source
- Applied and Computational Engineering
- Volume
- 230
- Issue
- 1
- Pages
- 60–67
- Publication date
- 30 March 2026
- Language
- EN