Advantages And Applications of Neural Hardware Based on Synapse Structure

Abstract

The increasing demand of computing power serves as a motivation for researchers to develop new types of hardware structures, among which the brain-inspired chip hardware show higher potential on computing power and energy consumption over traditional types. Memristors, which serve as a representative example of them, can allows a certain amount of current to pass safely and "remembers" the previous resistance value of the device after a power failure, which can be used as a perfect similar unit of neurons. Memristor can be manufactured by multiple material, such as various kind of metal oxides and have different of structure, classified by the number of memristors in each structure. However, the synaptic structure also faces great challenge to overcome, such as the uniformity of the capacity of each synaptic unit. In conclusion, memristor-based synapses for computing neural morphology have great potential for multiple applications, which can be perfect apply to the artificial intelligence industry.