Based on the basic device physics of the neuron-bipolar junction transistor (fBJT), a new compact cellular neural network (CNN) structure called the fBJT CNN is proposed and analyzed. In the fBJT CNN, both fBJT and lambda bipolar transistor realized by parasitic p-n-p BJTs in the CMOS process are used to implement the neuron whereas the coupling MOS resistors are used to realize the symmetric synapse weights among various neurons. Thus it has the advantages of small chip area and high integration capability. Moreover, the proposed symmetric fBJT CNN can be easily designed to achieve large neighborhood without extra interconnection. By adding a metal-layer optical window to the i'BJT, the i'BJT can be served as the phototransistor, and the i'BJT CNN can receive optical images as initial state inputs or external inputs. The correct functions of the fBJT CNNs in noise removal, hole filling, and erosion have been successfully verified in HSPICE simulation. An experimental chip containing a 32 x 32 fBJT CNN and a 16 X 16 fBJT CNN with phototransistor design, has been designed and fabricated in 0.6-4tm single-poly triple-metal n-well CMOS technology. The fabricated chips have the cell state transition time of 0.8 us and the static power consumption of 60 -4tW/cell. The area density can be as high as 1270 cells/mm2. The measurement results have also confirmed the correct functions of the proposed i'BJT CNNs.
|Number of pages||16|
|Journal||IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications|
|State||Published - 1 Dec 2001|
- Cellular neural network
- Large neighborhood