“知识神经元网络”KNN(Knowledge neural network)是一种以“神经元网络”模型 为基础的知识组织方法。 在“知识神经元网络”KNN 中,所谓的“知识”,是描述一个“知识”的文本,如一个网页、Word、PDF 文档等。

VIP内容

简介: “知识神经元网络”KNN(Knowledge neural network)是一种以“神经元网络”模型 为基础的知识组织方法。在现实中,“知识”通常是用文字进行叙述,知识蕴藏在自然语言叙述的内容和逻辑关系中。即便是抽象的数学知识,虽然采用数学符号语言进行定义和推导,但仍然离不开自然语言进行说明,否则很难被人理解。 在“知识神经元网络”KNN 中,所谓的“知识”,是描述一个“知识”的文本,如一个网页、Word、PDF 文档等。可从多维度(或仅一个)来描述“知识”。如,对一个疾病知识的描述,可有:症状、发病原因、检查手段、治疗方法等。 建立 KNN,首先将文本信息(网页、word、pdf 等)进行“知识化”处理,形成半结构化的“知识记录” ;然后,对“知识”进行相关性计算,使相关的“知识”建立连接,将杂乱无章、零星、无序的“知识” ,按相关性进行聚类,形成相互联通的“知识神经元网络”。

“知识神经元网络”KNN 的五个重要组成部分:

(1)“知识神经元”KN;

(2)“知识神经元连接”KNS;

(3)“知识神经元网络”KNN;

(4)“知识神经元网络桥”KNNB;

(5)“知识神经元网络系统”KNNS。

成为VIP会员查看完整内容
知识神经网络.pdf
0
9

最新论文

Data poisoning attacks and backdoor attacks aim to corrupt a machine learning classifier via modifying, adding, and/or removing some carefully selected training examples, such that the corrupted classifier makes incorrect predictions as the attacker desires. The key idea of state-of-the-art certified defenses against data poisoning attacks and backdoor attacks is to create a majority vote mechanism to predict the label of a testing example. Moreover, each voter is a base classifier trained on a subset of the training dataset. Classical simple learning algorithms such as k nearest neighbors (kNN) and radius nearest neighbors (rNN) have intrinsic majority vote mechanisms. In this work, we show that the intrinsic majority vote mechanisms in kNN and rNN already provide certified robustness guarantees against data poisoning attacks and backdoor attacks. Moreover, our evaluation results on MNIST and CIFAR10 show that the intrinsic certified robustness guarantees of kNN and rNN outperform those provided by state-of-the-art certified defenses. Our results serve as standard baselines for future certified defenses against data poisoning attacks and backdoor attacks.

0
0
下载
预览
Top