A New Smart Flash Memory Based On the Human Brain Structure by Using Trainable Transistor

In this paper, at first a new associative memory neural network is introduced and then a smart flash memory is presented which is based on a trainable transistor derived from a suggested neural network. The artificial neural network presented in this paper has a crystal type structure, which can be expanded easily. In training process of the network, each cell is trained individually and independently. Also, the applied inputs are not received directly from the outside world, but from a binary signature of them. This facilitates the implementation using VLSI. In order to implement the flash memory, each cell in the suggested neural network is replaced by a trainable transistor. Each trainable transistor has two wires for trapping or removing electrons in or from a floating gate. This new structure makes a fast trainable flash memory