電子發(fā)燒友網(wǎng)>電子資料下載>可編程邏輯>FPGA/ASIC>基于FPGA的人工神經(jīng)網(wǎng)絡(luò)系統(tǒng)的實(shí)現(xiàn)

基于FPGA的人工神經(jīng)網(wǎng)絡(luò)系統(tǒng)的實(shí)現(xiàn)

2512878 2010-11-25 | rar | 819 | 次下載 | 5積分

資料介紹

為了改變?nèi)斯?a href='http://www.wenjunhu.com/tags/神經(jīng)網(wǎng)絡(luò)/' target='_blank' class='arckwlink_none'>神經(jīng)網(wǎng)絡(luò)的研究?jī)H僅局限于算法，只是在通用的串行或并行計(jì)算機(jī)上模擬實(shí)現(xiàn)的現(xiàn)狀，針對(duì)函數(shù)逼近問(wèn)題，將BP神經(jīng)網(wǎng)絡(luò)的結(jié)構(gòu)分為3個(gè)模塊，采用VHDL語(yǔ)言完成對(duì)各個(gè)模塊的硬件描述，并使用Altera 公司的QuartusII 6. 1綜合軟件進(jìn)仿真和調(diào)試，然后在CycloneII系列FPGA上實(shí)現(xiàn)了能夠進(jìn)行片上學(xué)習(xí)并完成函數(shù)逼近的BP神經(jīng)網(wǎng)絡(luò)系統(tǒng)。測(cè)試結(jié)果證明，該系統(tǒng)能夠很好地完成在線學(xué)習(xí)，并能滿足一般系統(tǒng)應(yīng)用的速度和精度的要求，驗(yàn)證了該方法的有效性。

Abstract:: In order to change the situation that the research on the ANN only in algorithm and basing on serial or parallel general computer simulation， this paper focused on the function approximation and divided the BP neural network structure into three modules， it used VHDL to complete the description of hardware and the Altera company’s QuartusII 6.1 to simulate and debug，then implemented a BP neural network in the CycloneII series devices of FPGA produced by Altera company，this network coule completed the on-chip learning and the approximation of function. The test results show that the system can learn on-line and meet the general system applications- speed and accuracy.The system evaluates this method is effective.