no code implementations • 4 Jul 2023 • Tamas Madl, Weijie Xu, Olivia Choudhury, Matthew Howard
Despite progress in differential privacy and generative modeling for privacy-preserving data release in the literature, only a few approaches optimize for machine learning utility: most approaches only take into account statistical metrics on the data itself and fail to explicitly preserve the loss metrics of machine learning models that are to be subsequently trained on the generated data.
no code implementations • 17 Apr 2021 • Marina Y. Aoyama, Matthew Howard
Learning from demonstration (LfD) is commonly considered to be a natural and intuitive way to allow novice users to teach motor skills to robots.
no code implementations • 1 Mar 2020 • Jeevan Manavalan, Prabhakar Ray, Matthew Howard
The main advantage to using this is generalisation of a task by retargeting a systems redundancy as well as the capability to fully replace an entire system with another of varying link number and lengths while still accurately repeating a task subject to the same constraints.
1 code implementation • 4 Mar 2019 • Aran Sena, Brendan Michael, Matthew Howard
Learning from Demonstration depends on a robot learner generalising its learned model to unseen conditions, as it is not feasible for a person to provide a demonstration set that accounts for all possible variations in non-trivial tasks.
no code implementations • 12 Jul 2018 • Yuchen Zhao, Jeevan Manavalan, Prabhakar Ray, Hsiu-Chin Lin, Matthew Howard
This paper introduces the first, open source software library for Constraint Consistent Learning (CCL).
no code implementations • 11 Jul 2018 • Jeevan Manavalan, Matthew Howard
With the increase in complexity of robotic systems and the rise in non-expert users, it can be assumed that task constraints are not explicitly known.
no code implementations • 26 Jul 2016 • Hsiu-Chin Lin, Matthew Howard
In this paper, we consider learning the null space projection matrix of a kinematically constrained system in the absence of any prior knowledge either on the underlying policy, the geometry, or dimensionality of the constraints.