FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2883670420> ?p ?o ?g. }

• W2883670420 abstract "Gaussian Process (GP) regression has seen widespread use in robotics due to its generality, simplicity of use, and the utility of Bayesian predictions. The predominant implementation of GP regression is a nonparameteric kernel-based approach, as it enables fitting of arbitrary nonlinear functions. However, this approach suffers from two main drawbacks: (1) it is computationally inefficient, as computation scales poorly with the number of samples; and (2) it can be data inefficient, as encoding prior knowledge that can aid the model through the choice of kernel and associated hyperparameters is often challenging and unintuitive. In this work, we propose ALPaCA, an algorithm for efficient Bayesian regression which addresses these issues. ALPaCA uses a dataset of sample functions to learn a domain-specific, finite-dimensional feature encoding, as well as a prior over the associated weights, such that Bayesian linear regression in this feature space yields accurate online predictions of the posterior predictive density. These features are neural networks, which are trained via a meta-learning (or learning-to-learn) approach. ALPaCA extracts all prior information directly from the dataset, rather than restricting prior information to the choice of kernel hyperparameters. Furthermore, by operating in the weight space, it substantially reduces sample complexity. We investigate the performance of ALPaCA on two simple regression problems, two simulated robotic systems, and on a lane-change driving task performed by humans. We find our approach outperforms kernel-based GP regression, as well as state of the art meta-learning approaches, thereby providing a promising plug-in tool for many regression tasks in robotics where scalability and data-efficiency are important." @default.
• W2883670420 created "2018-08-03" @default.
• W2883670420 creator A5031821299 @default.
• W2883670420 creator A5048560900 @default.
• W2883670420 creator A5050003000 @default.
• W2883670420 date "2018-07-24" @default.
• W2883670420 modified "2023-09-27" @default.
• W2883670420 title "Meta-Learning Priors for Efficient Online Bayesian Regression" @default.
• W2883670420 cites W1502922572 @default.
• W2883670420 cites W1503398984 @default.
• W2883670420 cites W1870250857 @default.
• W2883670420 cites W1959608418 @default.
• W2883670420 cites W1977189000 @default.
• W2883670420 cites W1983607152 @default.
• W2883670420 cites W1995771589 @default.
• W2883670420 cites W2040100614 @default.
• W2883670420 cites W2097412577 @default.
• W2883670420 cites W2099768828 @default.
• W2883670420 cites W2123687908 @default.
• W2883670420 cites W2124609748 @default.
• W2883670420 cites W2127600800 @default.
• W2883670420 cites W2140135625 @default.
• W2883670420 cites W2144902422 @default.
• W2883670420 cites W2148522164 @default.
• W2883670420 cites W2162724919 @default.
• W2883670420 cites W2419216244 @default.
• W2883670420 cites W2472819217 @default.
• W2883670420 cites W2605916268 @default.
• W2883670420 cites W2620986852 @default.
• W2883670420 cites W2736601468 @default.
• W2883670420 cites W2762872434 @default.
• W2883670420 cites W2784596339 @default.
• W2883670420 cites W2787400134 @default.
• W2883670420 cites W2854287044 @default.
• W2883670420 cites W2950182411 @default.
• W2883670420 cites W2950277768 @default.
• W2883670420 cites W2951775809 @default.
• W2883670420 cites W2952677397 @default.
• W2883670420 cites W2952905979 @default.
• W2883670420 cites W2963266340 @default.
• W2883670420 cites W2963567641 @default.
• W2883670420 cites W2963641874 @default.
• W2883670420 cites W2964078140 @default.
• W2883670420 cites W2964121937 @default.
• W2883670420 cites W2964147651 @default.
• W2883670420 cites W3146166473 @default.
• W2883670420 hasPublicationYear "2018" @default.
• W2883670420 type Work @default.
• W2883670420 sameAs 2883670420 @default.
• W2883670420 citedByCount "10" @default.
• W2883670420 countsByYear W28836704202019 @default.
• W2883670420 countsByYear W28836704202020 @default.
• W2883670420 countsByYear W28836704202021 @default.
• W2883670420 crossrefType "posted-content" @default.
• W2883670420 hasAuthorship W2883670420A5031821299 @default.
• W2883670420 hasAuthorship W2883670420A5048560900 @default.
• W2883670420 hasAuthorship W2883670420A5050003000 @default.
• W2883670420 hasConcept C105795698 @default.
• W2883670420 hasConcept C107673813 @default.
• W2883670420 hasConcept C114614502 @default.
• W2883670420 hasConcept C119857082 @default.
• W2883670420 hasConcept C121332964 @default.
• W2883670420 hasConcept C138885662 @default.
• W2883670420 hasConcept C154945302 @default.
• W2883670420 hasConcept C160234255 @default.
• W2883670420 hasConcept C163716315 @default.
• W2883670420 hasConcept C177769412 @default.
• W2883670420 hasConcept C200695384 @default.
• W2883670420 hasConcept C2776401178 @default.
• W2883670420 hasConcept C33923547 @default.
• W2883670420 hasConcept C37903108 @default.
• W2883670420 hasConcept C41008148 @default.
• W2883670420 hasConcept C41895202 @default.
• W2883670420 hasConcept C61326573 @default.
• W2883670420 hasConcept C62520636 @default.
• W2883670420 hasConcept C74193536 @default.
• W2883670420 hasConcept C81692654 @default.
• W2883670420 hasConcept C83546350 @default.
• W2883670420 hasConcept C8642999 @default.
• W2883670420 hasConceptScore W2883670420C105795698 @default.
• W2883670420 hasConceptScore W2883670420C107673813 @default.
• W2883670420 hasConceptScore W2883670420C114614502 @default.
• W2883670420 hasConceptScore W2883670420C119857082 @default.
• W2883670420 hasConceptScore W2883670420C121332964 @default.
• W2883670420 hasConceptScore W2883670420C138885662 @default.
• W2883670420 hasConceptScore W2883670420C154945302 @default.
• W2883670420 hasConceptScore W2883670420C160234255 @default.
• W2883670420 hasConceptScore W2883670420C163716315 @default.
• W2883670420 hasConceptScore W2883670420C177769412 @default.
• W2883670420 hasConceptScore W2883670420C200695384 @default.
• W2883670420 hasConceptScore W2883670420C2776401178 @default.
• W2883670420 hasConceptScore W2883670420C33923547 @default.
• W2883670420 hasConceptScore W2883670420C37903108 @default.
• W2883670420 hasConceptScore W2883670420C41008148 @default.
• W2883670420 hasConceptScore W2883670420C41895202 @default.
• W2883670420 hasConceptScore W2883670420C61326573 @default.
• W2883670420 hasConceptScore W2883670420C62520636 @default.
• W2883670420 hasConceptScore W2883670420C74193536 @default.
• W2883670420 hasConceptScore W2883670420C81692654 @default.
• W2883670420 hasConceptScore W2883670420C83546350 @default.

• next