Search Results for author:
Found 7 papers, 1 papers with code
State-Denoised Recurrent Neural Networks
Attractor dynamics are incorporated into the hidden state to `clean up' representations at each step of a sequence.
Discrete Event, Continuous Time RNNs
The CT-GRU arises by interpreting the gates of a GRU as selecting a time scale of memory, and the CT-GRU generalizes the GRU by incorporating multiple time scales of memory and performing context-dependent selection of time scales for information storage and retrieval.
How deep is knowledge tracing?
In theoretical cognitive science, there is a tension between highly structured models whose parameters have a direct psychological interpretation and highly complex, general-purpose models whose parameters and representations are difficult to interpret.
Automatic Discovery of Cognitive Skills to Improve the Prediction of Student Learning
First, in three of the five datasets, the skills inferred by our technique support significantly improved predictions of student performance over the expert-provided skills.
Optimizing Instructional Policies
For example, in the domain of concept learning, a policy might specify the nature of exemplars chosen over a training sequence.
Improving Human Judgments by Decontaminating Sequential Dependencies
Our decontamination techniques yield an over 20% reduction in the error of human judgments.
Predicting the Optimal Spacing of Study: A Multiscale Context Model of Memory
MCM is intriguingly similar to a Bayesian multiscale model of memory (Kording, Tenenbaum, Shadmehr, 2007), yet MCM is better able to account for human declarative memory.
