Share This Author
Deep Knowledge Tracing
The utility of using Recurrent Neural Networks to model student learning and the learned model can be used for intelligent curriculum design and allows straightforward interpretation and discovery of structure in student tasks are explored.
Deconstructing disengagement: analyzing learner subpopulations in massive open online courses
A simple, scalable, and informative classification method is presented that identifies a small number of longitudinal engagement trajectories in MOOCs and compares learners in each trajectory and course across demographics, forum participation, video access, and reports of overall experience.
Tuned Models of Peer Assessment in MOOCs
Algorithms for estimating and correcting for grader biases and reliabilities are developed, showing significant improvement in peer grading accuracy on real data with 63,199 peer grades from Coursera's HCI course offerings --- the largest peer grading networks analysed to date.
On the Opportunities and Risks of Foundation Models
This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities, to their applications, and what they are even capable of due to their emergent properties.
Autonomously Generating Hints by Inferring Problem Solving Policies
This paper autonomously generate hints for the Code.org `Hour of Code,' (which is to the best of the authors' knowledge the largest online course to date) using historical student data, and discovers that this statistic is highly predictive of a student's future success.
Learning Program Embeddings to Propagate Feedback on Student Code
- C. Piech, Jonathan Huang, A. Nguyen, Mike Phulsuksombati, M. Sahami, L. Guibas
- Computer ScienceICML
- 22 May 2015
A neural network method is introduced to encode programs as a linear mapping from an embedded precondition space to an embedded postcondition space and an algorithm for feedback at scale is proposed using these linear maps as features.
Codewebs: scalable homework search for massive open online programming courses
A method for decomposing online homework submissions into a vocabulary of "code phrases", and based on this vocabulary, a queryable index that allows for fast searches into the massive dataset of student homework submissions is designed.
Programming Pluralism: Using Learning Analytics to Detect Patterns in the Learning of Computer Programming
- Paulo Blikstein, M. Worsley, C. Piech, M. Sahami, Steve Cooper, D. Koller
- Computer Science
- 4 September 2014
This article presents studies focused on how students learn computer programming, based on data drawn from 154,000 code snapshots of computer programs under development by approximately 370 students enrolled in an introductory undergraduate programming course, using methods from machine learning to discover patterns in the data and to predict final exam grades.
Modeling how students learn to program
This paper presents a methodology which uses machine learning techniques to autonomously create a graphical model of how students in an introductory programming course progress through a homework assignment, and shows that this model is predictive of which students will struggle with material presented later in the class.
Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction
An adversarially-trained neural network is presented that predicts recidivism and is trained to remove racial bias and gains predictive accuracy and gets closer to achieving two out of three measures of fairness: parity and equality of odds.