Deep-IRT: Make Deep Learning Based Knowledge Tracing Explainable Using Item Response Theory

Deep-IRT: Make Deep Learning Based Knowledge Tracing Explainable Using Item Response Theory

Student Ability and Difficulty Networks

$\text{DKVMN}$的模型架构可以被很容易的增强，进一步提供其他的有意义的信息。首先，每个潜在知识点的状态可以被拓展为学生能力。具体而言，当$\text{DKVMN}$模型接收一个知识点$q_t$时，会形成特征向量$f_t$。由于特征向量$f_t$是由读向量$r_t$和知识点嵌入向量$k^{}$