神經(jīng)記憶的電阻網(wǎng)絡(luò)綜合
RESISTIVE NETWORK SYNTHESIS FOR NEURAL MEMORY
-
摘要: 本文提出了從神經(jīng)系統(tǒng)功能進(jìn)行網(wǎng)絡(luò)綜合的觀點(diǎn)。對神經(jīng)網(wǎng)絡(luò)的記憶功能進(jìn)行了研究,建立了數(shù)學(xué)模型,并用分段線性電阻網(wǎng)絡(luò)進(jìn)行綜合。所得到的非線性電阻網(wǎng)絡(luò)除具有并行性、實(shí)時性、分布性和自適應(yīng)等一系列人工神經(jīng)網(wǎng)絡(luò)的特點(diǎn)外,網(wǎng)絡(luò)中各參數(shù)由網(wǎng)絡(luò)所應(yīng)記憶模式和特征向量的解析式給出,這比傳統(tǒng)的人工神經(jīng)網(wǎng)絡(luò)具有較強(qiáng)的直觀性,便于實(shí)際應(yīng)用。Abstract: It is suggested to study the neural network in the view of neural functions. The memory function of network is studied and its mathematical model is given. The model is synthesized by a peicewise-linear resistive network. The network is of many properties of artificial network such as parallelism, real-time processing, distributivity and adaptability etc., in addition, the parameters of network are expressed analytically by the patterns and features which are memorized in the network.
-
R.P. Lippmann, IEEE Trans. on ASSP, ASSP-4(1987)4,4-22.[2]夏征農(nóng)等,辭海(1979年版縮印本),上海辭書出版社,1985年,p.380.[3]Jack Y. Jau, Y.Fainman, Sing H. Lee, Applied Optics, 28(1989)2, 302-305.[4] B.Kosko, IEEE Trans. on SMC, SMC-18(1988)1,49-60.[4]蔡少棠, 非線性網(wǎng)絡(luò)理論引論(中冊),人民教育出版社,1980年. -
計(jì)量
- 文章訪問數(shù): 1908
- HTML全文瀏覽量: 132
- PDF下載量: 412
- 被引次數(shù): 0