Neural Belief Reasoner

2019-09-10 · Haifeng Qian

This paper proposes a new generative model called neural belief reasoner (NBR). It differs from previous models in that it specifies a belief function rather than a probability distribution. Its implementation consists of neural networks, fuzzy-set operations and belief-function operations, and query-answering, sample-generation and training algorithms are presented. This paper studies NBR in two tasks. The first is a synthetic unsupervised-learning task, which demonstrates NBR's ability to perform multi-hop reasoning, reasoning with uncertainty and reasoning about conflicting information. The second is supervised learning: a robust MNIST classifier for 4 and 9, which is the most challenging pair of digits. This classifier needs no adversarial training, and it substantially exceeds the state of the art in adversarial robustness as measured by the L2 metric, while at the same time maintains 99.1% accuracy on natural images.

📄 PDF Abstract BibTeX arXiv:1909.04719

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

PrivacyReasoner: Can LLM Emulate a Human-like Privacy Mind?

2026-01-14 · Yiwen Tu, Xuan Liu, Lianhui Qin, Haojian Jin arxiv

Prior work on LLM-based privacy focuses on norm judgment over synthetic vignettes, rather than how people think about a specific data practice and formulate their opinions. We address this gap by designing PrivacyReasone…

Combining Ontologies with Correspondences and Link Relations: The E-SHIQ Representation Framework

2013-10-09 · George A. Vouros, Georgios Santipantakis

Combining knowledge and beliefs of autonomous peers in distributed settings, is a ma- jor challenge. In this paper we consider peers that combine ontologies and reason jointly with their coupled knowledge. Ontologies are…

Interpreting Dynamical Systems as Bayesian Reasoners

2021-12-27 · Nathaniel Virgo, Martin Biehl, Simon McGregor

A central concept in active inference is that the internal states of a physical system parametrise probability measures over states of the external world. These can be seen as an agent's beliefs, expressed as a Bayesian …

Bayesian Inference

Language Models with Rationality

2023-05-23 · Nora Kassner, Oyvind Tafjord, Ashish Sabharwal, Kyle Richardson 외

While large language models (LLMs) are proficient at question-answering (QA), it is not always clear how (or even if) an answer follows from their latent "beliefs". This lack of interpretability is a growing impediment t…

Question Answering

Probabilistic Active Goal Recognition

2025-07-29 · Chenyuan Zhang, Cristian Rojas Cardenas, Hamid Rezatofighi, Mor Vered 외 arxiv

In multi-agent environments, effective interaction hinges on understanding the beliefs and intentions of other agents. While prior work on goal recognition has largely treated the observer as a passive reasoner, Active G…