Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
End-to-End Learnable Histogram Filters
Rico Jonschkowski, Oliver Brock
Nov 05, 2016 (modified: Jan 04, 2017)ICLR 2017 conference submissionreaders: everyone
Abstract:Problem-specific algorithms and generic machine learning approaches have complementary strengths and weaknesses, trading-off data efficiency and generality. To find the right balance between these, we propose to use problem-specific information encoded in algorithms together with the ability to learn details about the problem-instance from data. We demonstrate this approach in the context of state estimation in robotics, where we propose end-to-end learnable histogram filters---a differentiable implementation of histogram filters that encodes the structure of recursive state estimation using prediction and measurement update but allows the specific models to be learned end-to-end, i.e. in such a way that they optimize the performance of the filter, using either supervised or unsupervised learning.
TL;DR:a way to combine the algorithmic structure of Bayes filters with the end-to-end learnability of neural networks
Keywords:Deep learning, Unsupervised Learning
Enter your feedback below and we'll get back to you as soon as possible.