From Memory in our Brain to Emerging Resistive Memories in Neuromorphic Systems
Abstract
In this work, we will focus on the role that new nonvolatile resistive memory technologies (as OxRAM and CBRAM) can play in emerging fields of application, such as neuromorphic circuits, to save energy and increase performance. We will present large-scale energy efficient neuromorphic systems based on ReRAM as stochastic-binary synapses. Prototype applications such as complex visual- and auditory-pattern extraction will be discussed using feedforward spiking neural networks. A parallel will be drawn between these systems and human memory, as recent discoveries on the human brain and cognitive processes may bring benefits and open new perspectives for intelligent data processing.
Keywords
Brain
Cognitive systems
Complex networks
Data handling
Data reduction
Energy efficiency
Feedforward neural networks
Flip flop circuits
Neural networks
Parallel processing systems
Stochastic systems
artificial synapses
cognitive phenomena
Human memory
Neuromorphic circuits
ReRAM
Random access storage