Artificial neural networks with a specific autoencoding structure are capable of estimating parameters for the multidimensional logistic 2-parameter (ML2P) model in item response theory (Curi et al. in International joint conference on neural networks (IJCNN), 2019), but with limitations, such as uncorrelated latent traits. In this work, we extend variational auto encoders (VAE) to estimate item parameters and correlated latent abilities, and directly compare the ML2P-VAE method to more traditional parameter estimation methods, such as Monte Carlo expectation-maximization. The incorporation of a non-identity covariance matrix in a VAE requires a novel VAE architecture, which can be utilized in applications outside of education. In addition, we show that the ML2P-VAE method is capable of estimating parameters for models with a large number of latent variables with low computational cost, where traditional methods are infeasible for data with high-dimensional latent traits.

具有特定自动编码结构的人工神经网络能够估计项目响应理论中多维逻辑 2 参数 (ML2P) 模型的参数（Curi 等人在国际神经网络联合会议 (IJCNN)，2019 年），但有局限性，例如不相关的潜在特征。在这项工作中，我们扩展了变分自动编码器 (VAE) 来估计项目参数和相关的潜在能力，并直接将 ML2P-VAE 方法与更传统的参数估计方法（例如蒙特卡罗期望最大化）进行比较。在 VAE 中加入非恒等协方差矩阵需要一种新颖的 VAE 架构，该架构可用于教育以外的应用。此外，