Bayesian Optimization Meets Laplace Approximation for Robotic Introspection

by   Matthias Humt, et al.

In robotics, deep learning (DL) methods are used more and more widely, but their general inability to provide reliable confidence estimates will ultimately lead to fragile and unreliable systems. This impedes the potential deployments of DL methods for long-term autonomy. Therefore, in this paper we introduce a scalable Laplace Approximation (LA) technique to make Deep Neural Networks (DNNs) more introspective, i.e. to enable them to provide accurate assessments of their failure probability for unseen test data. In particular, we propose a novel Bayesian Optimization (BO) algorithm to mitigate their tendency of under-fitting the true weight posterior, so that both the calibration and the accuracy of the predictions can be simultaneously optimized. We demonstrate empirically that the proposed BO approach requires fewer iterations for this when compared to random search, and we show that the proposed framework can be scaled up to large datasets and architectures.



There are no comments yet.


page 1

page 5


BayesOpt: A Library for Bayesian optimization with Robotics Applications

The purpose of this paper is twofold. On one side, we present a general ...

Disentangling the Gauss-Newton Method and Approximate Inference for Neural Networks

In this thesis, we disentangle the generalized Gauss-Newton and approxim...

Expressive yet Tractable Bayesian Deep Learning via Subnetwork Inference

The Bayesian paradigm has the potential to solve some of the core issues...

Uncertainty aware multimodal activity recognition with Bayesian inference

Deep neural networks (DNNs) provide state-of-the-art results for a multi...

NSGZero: Efficiently Learning Non-Exploitable Policy in Large-Scale Network Security Games with Neural Monte Carlo Tree Search

How resources are deployed to secure critical targets in networks can be...

Deep Learning Methods for Universal MISO Beamforming

This letter studies deep learning (DL) approaches to optimize beamformin...

L2M: Practical posterior Laplace approximation with optimization-driven second moment estimation

Uncertainty quantification for deep neural networks has recently evolved...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.