arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.13348cs.LGcs.AIcs.CL
收藏

探索ML/DL架构在MNIST-1D数据集上的性能

Exploring the Performance of ML/DL Architectures on the MNIST-1D Dataset

Department of Computer Science Texas Tech University(计算机科学系德克萨斯技术大学)

Michael Beebe, GodsGift Uzor, Manasa Chepuri, Divya Sree Vemula, Angel Ayala

AI总结:

本文通过评估ResNet、TCN和DCNN等先进架构在MNIST-1D数据集上的性能,验证了其在小规模数据集中的优越性。

摘要:

小数据集如MNIST在推动机器学习研究方面历史上发挥了重要作用,通过提供受控环境进行快速实验和模型评估。然而,其简单性往往限制了其在区分先进神经网络架构之间的用途。为了解决这些挑战,Greydanus等人引入了MNIST-1D数据集,这是MNIST的一维改编版本,旨在探索序列数据中的归纳偏置。该数据集保留了小规模数据集的优势,同时引入了变化性和复杂性,使其成为研究先进架构的理想选择。在本文中,我们扩展了对MNIST-1D的探索,通过评估残差网络(ResNet)、时间卷积网络(TCN)和扩张卷积神经网络(DCNN)的性能。这些模型以其捕捉序列模式和层次特征的能力而闻名,并与之前测试的架构如逻辑回归、MLP、CNN和GRUs一起实现和基准测试。我们的实验结果表明,TCN和DCNN等先进架构在MNIST-1D上持续优于更简单的模型,达到接近人类性能。ResNet也显示出显著改进,突显了在小结构数据集中利用归纳偏置和层次特征提取的重要性。通过这项研究,我们验证了MNIST-1D作为在计算约束下评估机器学习架构的稳健基准的效用。我们的发现强调了架构创新在提高模型性能中的作用,并为在资源受限环境中优化深度学习模型提供了见解。

英文摘要:

Small datasets like MNIST have historically been instrumental in advancing machine learning research by providing a controlled environment for rapid experimentation and model evaluation. However, their simplicity often limits their utility for distinguishing between advanced neural network architectures. To address these challenges, Greydanus et al. introduced the MNIST-1D dataset, a one-dimensional adaptation of MNIST designed to explore inductive biases in sequential data. This dataset maintains the advantages of small-scale datasets while introducing variability and complexity that make it ideal for studying advanced architectures. In this paper, we extend the exploration of MNIST-1D by evaluating the performance of Residual Networks (ResNet), Temporal Convolutional Networks (TCN), and Dilated Convolutional Neural Networks (DCNN). These models, known for their ability to capture sequential patterns and hierarchical features, were implemented and benchmarked alongside previously tested architectures such as logistic regression, MLPs, CNNs, and GRUs. Our experimental results demonstrate that advanced architectures like TCN and DCNN consistently outperform simpler models, achieving near-human performance on MNIST-1D. ResNet also shows significant improvements, highlighting the importance of leveraging inductive biases and hierarchical feature extraction in small structured datasets. Through this study, we validate the utility of MNIST-1D as a robust benchmark for evaluating machine learning architectures under computational constraints. Our findings emphasize the role of architectural innovations in improving model performance and offer insights into optimizing deep learning models for resource-limited environments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑