Research on Optimization of Deep Learning in Handwritten Digit Recognition
Bibliographic record
Abstract
Aiming at the problem of balancing model accuracy and generalization ability in handwritten digit recognition tasks, this study takes the MNIST dataset as the research object, systematically compares the recognition performance of Multilayer Perceptrons (MLP) and Lightweight Convolutional Neural Networks (CNN). It optimizes model structures by adjusting the number of network layers, neurons, and convolution kernels, introduces Dropout regularization to suppress overfitting, and analyzes the impact of hyperparameters such as learning rate and batch size on model performance. Experimental results show that the lightweight CNN, relying on its advantage in spatial feature extraction, achieves a basic model recognition accuracy of 97.2%, significantly outperforming MLP's 95.8%. After structural optimization and Dropout regularization, the test accuracy of the lightweight CNN is improved to 98.6%, and overfitting is effectively alleviated. Among hyperparameters, the learning rate has the most significant impact on model convergence speed; when the optimal learning rate is 0.001, the model can quickly reach stable accuracy. This research provides an efficient lightweight model solution for handwritten digit recognition tasks, which is of reference value for image recognition applications in low-resource scenarios.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".