James M. Rehg

Towards Black-box Iterative Machine Teaching

2017 · arXiv (Cornell University)

In this paper, we make an important step towards the black-box machine teaching by considering the cross-space machine teaching, where the teacher and the learner use different feature representations and the teacher can not fully …

Kernel Deformed Exponential Families for Sparse Continuous Attention

2021 · arXiv (Cornell University)

Attention mechanisms take an expectation of a data representation with respect to probability weights. This creates summary statistics that focus on important features. Recently, (Martins et al. 2020, 2021) proposed continuous attention mechanisms, focusing on …

Approximate Inverse Reinforcement Learning from Vision-based Imitation\n Learning

2020 · arXiv (Cornell University)

In this work, we present a method for obtaining an implicit objective\nfunction for vision-based navigation. The proposed methodology relies on\nImitation Learning, Model Predictive Control (MPC), and an interpretation\ntechnique used in Deep Neural Networks. We use …