Study, fabrication and characterization of Leaky Integrate and Fire single component artificial neurons based on Mott insulators

Abstract

Since the 1960s, information technology has undergone a revolution due to the development of computers based on the Von Neumann architecture. While remarkably efficient for ultra-fast calculation, Von Neumann computers are outperformed by the mammal brain in several other data processing applications, such as data mining or pattern recognition. Neuromorphic computing aims at mimicking the brain behavior through the use of artificial neural networks.Since 2000, artificial intelligence is growing tremendously due to the development of artificial neural networks. These neural networks are mostly implemented at the software level on computers using the von Neumann architecture. As a consequence, they suffer from the main drawback of this architecture: energy consumption. A much more energy-efficient solution consists in implementing the neural network directly in the hardware, using both artificial neurons and synapses.