arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.04719cs.LGcs.AI
收藏

神经信念推理器

Neural Belief Reasoner

IBM Research(IBM研究院)

Haifeng Qian

摘要:

本文提出了一种新的生成模型称为神经信念推理机(NBR)。它与以前的模型不同之处在于它指定了一个置信函数而不是概率分布。它的实现包括神经网络、模糊集运算和置信函数运算,给出了查询应答、样本生成和训练算法。本文分两个方面对丁腈橡胶进行了研究。第一个是一个合成的无监督学习任务,它展示了NBR的能力,执行多跳推理,推理与不确定性和推理冲突的信息。第二个是监督学习:一个针对4和9的强大MNIST分类器,这是最具挑战性的一对数字。该分类器不需要对抗训练,并且它在对抗鲁棒性方面大大超过了L2度量的最新水平,同时在自然图像上保持了99.1%的准确率。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑