Knowledge Transfer in a Pair of Uniformly Modelled Bayesian Filters

Jirsa, Ladislav; Pavelková, Lenka; Quinn, Anthony

doi:10.5220/0007854104990506

Cited by 4 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current paper significantly extends and formalizes results on BTL reported in the above-mentioned authors' papers [22] and [23]. Both of those papers report an improvement in target performance in the case of concentrated source knowledge (positive transfer) and rejection of diffuse source knowledge (robust transfer).…”

Section: Introductionsupporting

confidence: 79%

“…• In the authors' previous publications [22], [23], [39], it was the source data predictor which was transferred. Instead, here, for the first time, it is the source state predictor, f S (x S,t |d S (t − 1)), t ∈ T, that is transferred.…”

Section: Fpd-optimal Bayesian Transfer Learning (Fpd-btl)mentioning

confidence: 99%

“…The interval, ϕ ∈ (−0.007, 0.067), represents the range (found experimentally) when X ∩ t = ∅ in Theorem 1, and the estimation is numerically stable, i.e. the intersection in (22) is nonempty. To repeat: the data are synthesized with ϕ = 0,…”

Section: Modelling Mismatchmentioning

confidence: 99%

“…They avoid the adoption of unbounded noises, that can lead to over-conservative design [21]. To the best of our knowledge, the topic of BTL-based multi-task/filter state estimation with bounded noises has not yet been addressed in the literature, except in the author's previous publications [22,23]. In those papers, BTL between a pair of filters affected by bounded noises is presented.…”

Section: Introductionmentioning

confidence: 99%

“…The optimal target state filtering distribution is then designed via FPD. In [22], the support of the state inference is an orthotope, while in [23], it is relaxed to a parallelotope.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Fully probabilistic design for knowledge fusion between Bayesian filters under uniform disturbances

Pavelková¹,

Jirsa²,

Quinn³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

This paper considers the problem of Bayesian transfer learning-based knowledge fusion between linear state-space processes driven by uniform state and observation noise processes. The target task conditions on probabilistic state predictor(s) supplied by the source filtering task(s) to improve its own state estimate. A joint model of the target and source(s) is not required and is not elicited. The resulting decision-making problem for choosing the optimal conditional target filtering distribution under incomplete modelling is solved via fully probabilistic design (FPD), i.e. via appropriate minimization of Kullback-Leibler divergence (KLD). The resulting FPD-optimal target learner is robust, in the sense that it can reject poor-quality source knowledge. In addition, the fact that this Bayesian transfer learning (BTL) scheme does not depend on a model of interaction between the source and target tasks ensures robustness to the misspecification of such a model. The latter is a problem that affects conventional transfer learning methods. The properties of the proposed BTL scheme are demonstrated via extensive simulations, and in comparison with two contemporary alternatives.

show abstract

Section: Introductionsupporting

confidence: 79%

Section: Fpd-optimal Bayesian Transfer Learning (Fpd-btl)mentioning

confidence: 99%

Section: Modelling Mismatchmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…The optimal target state filtering distribution is then designed via FPD. In [22], the support of the state inference is an orthotope, while in [23], it is relaxed to a parallelotope.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations