What question did this study set out to answer?

The aim is to compare classical machine learning and deep learning approaches for handwritten digit recognition using the MNIST dataset.

May 21, 2026Open Access

MNIST Digit Classification Comparative Analysis of Machine Learning and Deep Learning Approaches

View Full Paper

Ask AI

Bookmark

Authors

MNmd. saddab niyazi IMindrajeet mandal HKH. Ajay KumarSRM University

Discussion

Member takes

Implication

This comparative analysis evaluates digit classification performance in the MNIST dataset, highlighting implications for model selection in various contexts.

Key Points

The aim is to compare classical machine learning and deep learning approaches for handwritten digit recognition using the MNIST dataset.
Examined Logistic Regression, ANN, and CNN for classification tasks.
Evaluated models based on accuracy, computational efficiency, model complexity, and robustness to input variations.
Conducted systematic experiments under controlled benchmark conditions.
CNNs achieved the highest classification accuracy due to effective spatial feature extraction.
Logistic Regression and ANN demonstrated competitive speed and interpretability.
Trade-offs between model simplicity and performance were evident, particularly under resource constraints.

Cite This Study

niyazi et al. (2026) studied this question.

synapsesocial.com/papers/6a0ea127be05d6e3efb5f912 https://doi.org/10.5281/zenodo.20293022

View Full Paper

Ask AI

Bookmark

Implication

This comparative analysis evaluates digit classification performance in the MNIST dataset, highlighting implications for model selection in various contexts.

MNIST Digit Classification Comparative Analysis of Machine Learning and Deep Learning Approaches

Discussion

Member takes

Implication

Key Points

Cite This Study

MNIST Digit Classification Comparative Analysis of Machine Learning and Deep Learning Approaches

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider