抗體網(wǎng)絡(luò)作為一種新型的基于免疫原理的神經(jīng)網(wǎng)絡(luò)模型，已有的實(shí)驗(yàn)驗(yàn)證了其具有良好的無監(jiān)督競(jìng)爭(zhēng)學(xué)習(xí)能力。但對(duì)抗體網(wǎng)絡(luò)的研究目前還集中在原理介紹和實(shí)驗(yàn)驗(yàn)證上，沒有將其應(yīng)用在實(shí)際工程問題中的先例。在保留抗體網(wǎng)絡(luò)的結(jié)構(gòu)自動(dòng)生成，基于克隆選擇、變異機(jī)制的無監(jiān)督競(jìng)爭(zhēng)學(xué)習(xí)等優(yōu)點(diǎn)的同時(shí)，對(duì)抗體網(wǎng)絡(luò)的初始化、抗體的表示方式、網(wǎng)絡(luò)結(jié)構(gòu)的更新等方面作了適當(dāng)?shù)母倪M(jìn)。在此基礎(chǔ)上設(shè)計(jì)的郵件過濾器，和傳統(tǒng)的郵件過濾器相比，實(shí)驗(yàn)結(jié)果表明其具有自適應(yīng)能力好、準(zhǔn)確性高等優(yōu)點(diǎn)。
關(guān) 鍵 詞 垃圾郵件; 郵件過濾器; 抗體網(wǎng)絡(luò); 克隆選擇; 人工神經(jīng)網(wǎng)絡(luò)

Abstract The Antibody Network(ABNET),which is a new ANN based on immune principle,has been proved to have good ability of unsupervised and competitive learning in experiments.But there is no precedent to use ABNET in practical engineerings because the present researches about it are still focusing on principle and experiments. While the good qualities of ABNET are reserved,such as structure generated automatically, unsupervised and competitive learning based on clone selection and mutation,the way of initiating ABNET, expressing a antibody, updating structure is improved properly.The mail filter based on improved ABNET is better at adaptation and accuracy in experiments,compared with traditional mail filters.
Key words spam; mail filter; ABNET; clonal selection; ANN