Proceedings of the 1st Annual Conference on Robot Learning on 13-15 November 2017 Published as Volume 78 by the Proceedings of Machine Learning Research on 18 October 2017. Volume Edited by: Sergey Levine Vincent Vanhoucke Ken Goldberg Series Editors: Neil D. Lawrence Mark Reid
Today I successfully submitted my first paper to arXiv! We've submitted this paper to a journal, but it hasn't been published yet, so we wanted to get a pre-print up before advertising the corresponding software packages. Unfortunately, the process of submitting to arXiv wasn't painless. Now that I've figured out some of the quirks, however, hopefully your…
Write Your Research provides practical resources for early-career researchers in the School of Technology, University of Cambridge. The resources were commissioned by the Department of Chemical Engineering and Biotechnology (CEB). Most of the resources were written by Anthony Haynes. 'Using social media' was written by Aoife Brophy Haney. 'Using bibliographic software' was written by Irenee…
Multiple Instance Learning (mil) Is A Variation Of Supervised Learning Where A Single Class Label Is Assigned To A Bag Of Instances. In This Paper, We State The Mil Problem As Learning The Bernoulli Distribution Of The Bag Label Where The Bag Label Probability Is Fully Parameterized By Neural Networks. Furthermore, We Propose A Neural Network-based Permutation-invariant Aggregation Operator That Corresponds To The Attention Mechanism. Notably, An Application Of The Proposed Attention-based Operator Provides Insight Into The Contribution Of Each Instance To The Bag Label. We Show Empirically That Our Approach Achieves Comparable Performance To The Best Mil Methods On Benchmark Mil Datasets And It Outperforms Other Methods On A Mnist-based Mil Dataset And Two Real-life Histopathology Datasets Without Sacrificing Interpretability.
Interacting Systems Are Prevalent In Nature, From Dynamical Systems In Physics To Complex Societal Dynamics. The Interplay Of Components Can Give Rise To Complex Behavior, Which Can Often Be Explained Using A Simple Model Of The System's Constituent Parts. In This Work, We Introduce The Neural Relational Inference (nri) Model: An Unsupervised Model That Learns To Infer Interactions While Simultaneously Learning The Dynamics Purely From Observational Data. Our Model Takes The Form Of A Variational Auto-encoder, In Which The Latent Code Represents The Underlying Interaction Graph And The Reconstruction Is Based On Graph Neural Networks. In Experiments On Simulated Physical Systems, We Show That Our Nri Model Can Accurately Recover Ground-truth Interactions In An Unsupervised Manner. We Further Demonstrate That We Can Find An Interpretable Structure And Predict Complex Dynamics In Real Motion Capture And Sports Tracking Data.