Skip to main content
. 2012 Apr 10;11:18. doi: 10.1186/1475-925X-11-18

Table 4.

Area and performance comparison between FPGA-based Hebbi an eigenfilter and PCA

Hebbian eigenfilter Stream-based HE PCA Improvement
(HE) (SHE) [32] (SHE vs PCA)

Number of slice 897 749 7722 10.3x

Number of BRAM 65 5 65 13x

Power (mW) 7.3 2.4 49.3 20.5x

Learning latency (μs ) 5.6 5.6 42.4 7.6x