Search

In recent days, more hardware-driven artificial intelligence system capable of brain-like low-energy consumption is gaining ever-increasing interest. The hardware-driven property lies in the low-power synaptic device and its array along with the area and energy-efficient neuron circuits. In this work, a spiking neural network (SNN) based on analog synaptic device of resistive-switching random access memory (RRAM) is constructed from the experimentally fabricated devices. Furthermore, the capability of the designed SNN hardware for sequential tasks through an optimal reinforcement learning (RL) algorithm is demonstrated. More specifically, the Rush Hour game is conducted as an example of applications for the sequential task for which an SNN architecture is plausibly suited. The rule of the game is simple but has not been demonstrated by a hardware-oriented artificial neural network (ANN) yet, and in this work, it is reported that the analog RRAM synaptic devices in the cross-point array architecture successfully solve the problem via the RL algorithm. [ABSTRACT FROM AUTHOR]

We fabricated a silicon based nano-wedge resistive switching memory device with the stack of Ti/HfOx/p+-Si. By using 25% tetra-methyl-ammonium hydroxide (TMAH) aqueous solution, the anisotropic wet etching process is carried out to minimize the tip structure of the silicon bottom electrode to a width of 4 nm, and the structure was validated through TEM analysis. Due to the minimized device area, low read current levels (<1 μA) were obtained in the nano-wedge RRAM while the opposites were measured in large size RRAM devices. In addition, the fabricated nano-wedge RRAM exhibited low power consumption during the DC switching process. Additionally, pulse measurement and retention tests were performed to demonstrate the synaptic behaviors of long-term potentiation and depression. Software neural network simulation was followed to test the feasibility of nano-wedge RRAM's array implementation. These results demonstrate the fabricated nano-wedge RRAM devices' potential usage as a synaptic device in neuromorphic computing systems. [ABSTRACT FROM AUTHOR]