首个缅甸手写数字识别基准，对比了多种模型性能。
myMNIST: Benchmark of PETNN, KAN, and Classical Deep Learning Models for Burmese Handwritten Digit Recognition
- 构建标准数据集myMNIST，评估11种模型在缅甸手写数字上的表现。
- CNN表现最优（准确率99.70%，F1值0.9959），PETNN(GELU)紧随其后。
- 首次系统对比物理启发模型与经典/新兴模型，适合关注区域语言识别的研究者。
我们提出了首个针对公开的缅甸手写数字数据集（BHDD）的系统性基准测试，命名为myMNIST Benchmarking。尽管BHDD是缅甸NLP/AI的基础资源，但缺乏在现代架构下的全面、可复现性能基线。我们评估了涵盖经典深度学习模型（多层感知机、卷积神经网络、长短期记忆、门控循环单元、Transformer）、近期替代方案（FastKAN、EfficientKAN）、能量模型（JEM）以及物理启发的PETNN变体（Sigmoid、GELU、SiLU）在内的11种架构。使用精确率、召回率、F1分数和准确率作为评估指标，结果显示，卷积神经网络仍为强基线，取得最佳综合表现（F1=0.9959，准确率=0.9970）。PETNN(GELU)表现接近（F1=0.9955，准确率=0.9966），优于LSTM、GRU、Transformer及KAN变体。能量模型JEM表现具有竞争力（F1=0.9944，准确率=0.9958）。基于KAN的模型（FastKAN、EfficientKAN）略逊但提供有意义的备选基线（准确率约0.992）。研究结果（i）建立了跨多种建模范式的可复现基线，（ii）凸显PETNN相对于经典与Transformer模型的优异表现，（iii）量化了物理启发的PETNN与真实能量模型（JEM）之间的差距。我们发布该基准以促进缅甸数字识别的未来研究，并鼓励对新兴架构在区域性文字上的评估。
原文摘要 · Abstract (English)
We present the first systematic benchmark on a standardized iteration of the publicly available Burmese Handwritten Digit Dataset (BHDD), which we have designated as myMNIST Benchmarking. While BHDD serves as a foundational resource for Myanmar NLP/AI, it lacks a comprehensive, reproducible performance baseline across modern architectures. 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 BHDD 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。