CAPACITANCE-BASED MATRIX MULTIPLICATION NEURAL NETWORK BY CONTROLLING INPUT WITH PULSE COUNTS AND WEIGHTS WITH VOLTAGE

摘要

A capacitance-based matrix multiplication neural network for matching the number of pulses to an input signal and adjusting a weight with a voltage according to an embodiment of the present invention includes a word line, a bit line, a transistor connected to a capacitor, and a capacitor connected to the transistor. However, the input of the bit line is connected to a pulse generator, the output is connected to a sense amplifier, and the weight is adjusted by the voltage applied to the capacitor.