Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

myMNIST: Benchmark of PETNN, KAN, and Classical Deep Learning Models for Burmese Handwritten Digit Recognition

Ye Kyaw Thu, Thazin Myint Oo, Thepchai Supnithi

Abstract

We present the first systematic benchmark on myMNIST (formerly BHDD), a publicly available Burmese handwritten digit dataset important for Myanmar NLP/AI research. We evaluate eleven architectures spanning classical deep learning models (Multi-Layer Perceptron, Convolutional Neural Network, Long Short-Term Memory, Gated Recurrent Unit, Transformer), recent alternatives (FastKAN, EfficientKAN), an energy-based model (JEM), and physics-inspired PETNN variants (Sigmoid, GELU, SiLU). Using Precision, Recall, F1-Score, and Accuracy as evaluation metrics, our results show that the CNN remains a strong baseline, achieving the best overall scores (F1 = 0.9959, Accuracy = 0.9970). The PETNN (GELU) model closely follows (F1 = 0.9955, Accuracy = 0.9966), outperforming LSTM, GRU, Transformer, and KAN variants. JEM, representing energy-based modeling, performs competitively (F1 = 0.9944, Accuracy = 0.9958). KAN-based models (FastKAN, EfficientKAN) trail the top performers but provide a meaningful alternative baseline (Accuracy ~0.992). These findings (i) establish reproducible baselines for myMNIST across diverse modeling paradigms, (ii) highlight PETNN's strong performance relative to classical and Transformer-based models, and (iii) quantify the gap between energy-inspired PETNNs and a true energy-based model (JEM). We release this benchmark to facilitate future research on Myanmar digit recognition and to encourage broader evaluation of emerging architectures on regional scripts.

myMNIST: Benchmark of PETNN, KAN, and Classical Deep Learning Models for Burmese Handwritten Digit Recognition

Abstract

We present the first systematic benchmark on myMNIST (formerly BHDD), a publicly available Burmese handwritten digit dataset important for Myanmar NLP/AI research. We evaluate eleven architectures spanning classical deep learning models (Multi-Layer Perceptron, Convolutional Neural Network, Long Short-Term Memory, Gated Recurrent Unit, Transformer), recent alternatives (FastKAN, EfficientKAN), an energy-based model (JEM), and physics-inspired PETNN variants (Sigmoid, GELU, SiLU). Using Precision, Recall, F1-Score, and Accuracy as evaluation metrics, our results show that the CNN remains a strong baseline, achieving the best overall scores (F1 = 0.9959, Accuracy = 0.9970). The PETNN (GELU) model closely follows (F1 = 0.9955, Accuracy = 0.9966), outperforming LSTM, GRU, Transformer, and KAN variants. JEM, representing energy-based modeling, performs competitively (F1 = 0.9944, Accuracy = 0.9958). KAN-based models (FastKAN, EfficientKAN) trail the top performers but provide a meaningful alternative baseline (Accuracy ~0.992). These findings (i) establish reproducible baselines for myMNIST across diverse modeling paradigms, (ii) highlight PETNN's strong performance relative to classical and Transformer-based models, and (iii) quantify the gap between energy-inspired PETNNs and a true energy-based model (JEM). We release this benchmark to facilitate future research on Myanmar digit recognition and to encourage broader evaluation of emerging architectures on regional scripts.
Paper Structure (25 sections, 10 equations, 2 figures, 3 tables)

This paper contains 25 sections, 10 equations, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Burmese Handwritten Digit Recognition
  3. ConvNet on the Burmese Handwritten Digits Dataset (BHDD)
  4. Architectural Refinement and Deployment
  5. Classical Deep Learning Models
  6. Multilayer Perceptron (MLP)
  7. Convolutional Neural Network (CNN)
  8. Long Short-Term Memory (LSTM)
  9. Gated Recurrent Unit (GRU)
  10. Transformer
  11. Joint Energy Model (JEM)
  12. Kolmogorov-Arnold Networks (KAN)
  13. Physics-inspired Energy Transition NN (PETNN)
  14. Experimental Setting
  15. Dataset: myMNIST (BHDD)
  16. ...and 10 more sections

Figures (2)

  • Figure 1: Visualization of the myMNIST (BHDD) dataset. The figure displays five randomly selected samples for each of the ten Burmese digit classes (0-9), illustrating the variety of handwriting styles present in the dataset.
  • Figure 2: Confusion matrices for the evaluated models, highlighting common misclassification patterns.