nach oben

2024 | Buch

Kapitel lesen Erstes Kapitel lesen

Epistemic Uncertainty in Artificial Intelligence

First International Workshop, Epi UAI 2023, Pittsburgh, PA, USA, August 4, 2023, Revised Selected Papers

herausgegeben von: Fabio Cuzzolin, Maryam Sultana

Verlag: Springer Nature Switzerland

Buchreihe : Lecture Notes in Computer Science

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

This LNCS 14523 conference volume constitutes the proceedings of the First International Workshop, Epi UAI 2023, in Pittsburgh, PA, USA, August 2023. The 8 full papers together included in this volume were carefully reviewed and selected from 16 submissions.

Epistemic AI focuses, in particular, on some of the most important areas of machine learning: unsupervised learning, supervised learning, and reinforcement learning.

Inhaltsverzeichnis

Frontmatter

A Novel Bayes’ Theorem for Upper Probabilities

Abstract

In their seminal 1990 paper, Wasserman and Kadane establish an upper bound for the Bayes’ posterior probability of a measurable set A, when the prior lies in a class of probability measures \(\mathcal {P}\) and the likelihood is precise. They also give a sufficient condition for such upper bound to hold with equality. In this paper, we introduce a generalization of their result by additionally addressing uncertainty related to the likelihood. We give an upper bound for the posterior probability when both the prior and the likelihood belong to a set of probabilities. Furthermore, we give a sufficient condition for this upper bound to become an equality. This result is interesting on its own, and has the potential of being applied to various fields of engineering (e.g. model predictive control), machine learning, and artificial intelligence.

Michele Caprio, Yusuf Sale, Eyke Hüllermeier, Insup Lee

Deep Learning and MCMC with aggVAE for Shifting Administrative Boundaries: Mapping Malaria Prevalence in Kenya

Abstract

Model-based disease mapping remains a fundamental policy-informing tool in the fields of public health and disease surveillance. Hierarchical Bayesian models have emerged as the state-of-the-art approach for disease mapping since they are able to both capture structure in the data and robustly characterise uncertainty. When working with areal data, e.g. aggregates at the administrative unit level such as district or province, current models rely on the adjacency structure of areal units to account for spatial correlations and perform shrinkage. The goal of disease surveillance systems is to track disease outcomes over time. This task is especially challenging in crisis situations which often lead to redrawn administrative boundaries, meaning that data collected before and after the crisis are no longer directly comparable. Moreover, the adjacency-based approach ignores the continuous nature of spatial processes and cannot solve the change-of-support problem, i.e. when estimates are required to be produced at different administrative levels or levels of aggregation. We present a novel, practical, and easy to implement solution to solve these problems relying on a methodology combining deep generative modelling and fully Bayesian inference: we build on the recently proposed PriorVAE method able to encode spatial priors over small areas with variational autoencoders by encoding aggregates over administrative units. We map malaria prevalence in Kenya, a country in which administrative boundaries changed in 2010.

Elizaveta Semenova, Swapnil Mishra, Samir Bhatt, Seth Flaxman, H Juliette T Unwin

Bag of Policies for Distributional Deep Exploration

Abstract

Efficient exploration in complex environments remains a major challenge for reinforcement learning (RL). Compared to previous Thompson sampling-inspired mechanisms that enable temporally extended exploration, i.e., deep exploration, we focus on deep exploration in distributional RL. We develop a general purpose approach, Bag of Policies (BoP), that can be built on top of any return distribution estimator by maintaining a population of its copies. BoP consists of an ensemble of multiple heads that are updated independently. During training, each episode is controlled by only one of the heads and the collected state-action pairs are used to update all heads off-policy, leading to distinct learning signals for each head which diversify learning and behaviour. To test whether optimistic ensemble method can improve on distributional RL as it does on scalar RL, we implement the BoP approach with a population of distributional actor-critics using Bayesian Distributional Policy Gradients (BDPG). The population thus approximates a posterior distribution of return distributions along with a posterior distribution of policies. Our setup allows to analyze global posterior uncertainty along with local curiosity bonus simultaneously for exploration. As BDPG is already an optimistic method, this pairing helps to investigate the extent to which accumulating curiosity bonuses is beneficial. Overall BoP results in greater robustness and speed during learning as demonstrated by our experimental results on ALE Atari games.

Asen Nachkov, Luchen Li, Giulia Luise, Filippo Valdettaro, A. Aldo Faisal

Defensive Perception: Estimation and Monitoring of Neural Network Performance Under Deployment

Abstract

In this paper, we propose a method for addressing the issue of unnoticed catastrophic deployment and domain shift in neural networks for semantic segmentation in autonomous driving. Our approach is based on the idea that deep learning-based perception for autonomous driving is uncertain and best represented as a probability distribution. As autonomous vehicles’ safety is paramount, it is crucial for perception systems to recognize when the vehicle is leaving its operational design domain, anticipate hazardous uncertainty, and reduce the performance of the perception system. To address this, we propose to encapsulate the neural network under deployment within an uncertainty estimation envelope that is based on the epistemic uncertainty estimation through the Monte Carlo Dropout approach. This approach does not require modification of the deployed neural network and guarantees expected model performance. Our defensive perception envelope has the capability to estimate a neural network’s performance, enabling monitoring and notification of entering domains of reduced neural network performance under deployment. Furthermore, our envelope is extended by novel methods to improve the application in deployment settings, including reducing compute expenses and confining estimation noise. Finally, we demonstrate the applicability of our method for multiple different potential deployment shifts relevant to autonomous driving, such as transitions into the night, rainy, or snowy domain. Overall, our approach shows great potential for application in deployment settings and enables operational design domain recognition via uncertainty, which allows for defensive perception, safe state triggers, warning notifications, and feedback for testing or development and adaptation of the perception stack.

Hendrik Vogt, Stefan Buehler, Mark Schutera

Towards Understanding the Interplay of Generative Artificial Intelligence and the Internet

Abstract

The rapid adoption of generative Artificial Intelligence (AI) tools that can generate realistic images or text, such as DALL-E, MidJourney, or ChatGPT, have put the societal impacts of these technologies at the center of public debate. These tools are possible due to the massive amount of data (text and images) that is publicly available through the Internet. At the same time, these generative AI tools become content creators that are already contributing to the data that is available to train future models. Therefore, future versions of generative AI tools will be trained with a mix of human-created and AI-generated content, causing a potential feedback loop between generative AI and public data repositories. This interaction raises many questions: how will future versions of generative AI tools behave when trained on a mixture of real and AI-generated data? Will they evolve and improve with the new data sets or on the contrary will they degrade? Will evolution introduce biases or reduce diversity in subsequent generations of generative AI tools? What are the societal implications of the possible degradation of these models? Can we mitigate the effects of this feedback loop? In this work, we explore the effect of this interaction and report some initial results using simple diffusion models trained with various image datasets. Our results show that the quality and diversity of the generated images can degrade over time suggesting that incorporating AI-created data can have undesired effects on future versions of generative models.

Gonzalo Martínez, Lauren Watson, Pedro Reviriego, José Alberto Hernández, Marc Juarez, Rik Sarkar

Optimizing Brain Tumor Classification: A Comprehensive Study on Transfer Learning and Imbalance Handling in Deep Learning Models

Abstract

Deep learning has emerged as a prominent field in recent literature, showcasing the introduction of models that utilize transfer learning to achieve remarkable accuracies in the classification of brain tumor MRI images. However, the majority of these proposals primarily focus on balanced datasets, neglecting the inherent data imbalance present in real-world scenarios. Consequently, there is a pressing need for approaches that not only address the data imbalance but also prioritize precise classification of brain cancer. In this work, we present a novel deep learning-based approach, called Transfer Learning-CNN, for brain tumor classification using MRI data. The proposed model leverages the predictive capabilities of existing publicly available models by utilizing their pre-trained weights and transferring those weights to the CNN. By leveraging a publicly available Brain MRI dataset, the experiment evaluated various transfer learning models for classifying different tumor types, including meningioma, glioma, and pituitary tumors. We investigate the impact of different loss functions, including focal loss, and oversampling methods, such as SMOTE and ADASYN, in addressing the data imbalance issue. Notably, the proposed strategy, which combines VGG-16 and CNN, achieved an impressive accuracy rate of 96%, surpassing alternative approaches significantly. Our code is available at Github.

Raza Imam, Mohammed Talha Alam

Towards Offline Reinforcement Learning with Pessimistic Value Priors

Abstract

Offline reinforcement learning (RL) seeks to train agents in sequential decision-making tasks using only previously collected data and without directly interacting with the environment. As the agent tries to improve on the policy present in the dataset, it can introduce distributional shift between the training data and the suggested agent’s policy which can lead to poor performance. To avoid the agent assigning high values to out-of-distribution actions, successful offline RL requires some form of conservatism to be introduced. Here we present a model-free inference framework that encodes this conservatism in the prior belief of the value function: by carrying out policy evaluation with a pessimistic prior, we ensure that only the actions that are directly supported by the offline dataset will be modelled as having a high value. In contrast to other methods, we do not need to introduce heuristic policy constraints, value regularisation or uncertainty penalties to achieve successful offline RL policies in a toy environment. An additional consequence of our work is a principled quantification of Bayesian uncertainty in off-policy returns in model-free RL. While we are able to present an implementation of this framework to verify its behaviour in the exact inference setting with Gaussian processes on a toy problem, the scalability issues that it suffers as the central avenue for further work. We address in more detail these limitations and consider future directions to improve the scalability of this framework beyond the vanilla Gaussian process implementation, proposing a path towards improving offline RL algorithms in a principled way.

Filippo Valdettaro, A. Aldo Faisal

Semantic Attribution for Explainable Uncertainty Quantification

Abstract

Bayesian deep learning, with an emphasis on uncertainty quantification, is receiving growing interest in building reliable models. Nonetheless, interpreting and explaining the origins and reasons for uncertainty presents a significant challenge. In this paper, we present semantic uncertainty attribution as a tool for pinpointing the primary factors contributing to uncertainty. This approach allows us to explain why a particular image carries high uncertainty, thereby making our models more interpretable. Specifically, we utilize the variational autoencoder to disentangle different semantic factors within the latent space and link the uncertainty to corresponding semantic factors for an explanation. The proposed techniques can also enhance explainable out-of-distribution (OOD) detection. We can not only identify OOD samples via their uncertainty, but also provide reasoning rooted in a semantic concept.

Hanjing Wang, Shiqiang Wang, Qiang Ji

Backmatter

Titel: Epistemic Uncertainty in Artificial Intelligence
herausgegeben von: Fabio Cuzzolin
Maryam Sultana
Verlag: Springer Nature Switzerland
Electronic ISBN: 978-3-031-57963-9
Print ISBN: 978-3-031-57962-2
DOI: https://doi.org/10.1007/978-3-031-57963-9

Springer Professional

Über dieses Buch

Inhaltsverzeichnis

Frontmatter

A Novel Bayes’ Theorem for Upper Probabilities

Deep Learning and MCMC with aggVAE for Shifting Administrative Boundaries: Mapping Malaria Prevalence in Kenya

Bag of Policies for Distributional Deep Exploration

Defensive Perception: Estimation and Monitoring of Neural Network Performance Under Deployment

Towards Understanding the Interplay of Generative Artificial Intelligence and the Internet

Optimizing Brain Tumor Classification: A Comprehensive Study on Transfer Learning and Imbalance Handling in Deep Learning Models

Towards Offline Reinforcement Learning with Pessimistic Value Priors

Semantic Attribution for Explainable Uncertainty Quantification

Backmatter

Premium Partner