Neuromorphic Processing Devices

Abstract

A neuromorphic processing device (1) has a device input (2) and a set of neuron circuits (3) for receiving input data signals. Each neuron circuit (3) comprises a resistive memory unit (14) and a neuron output circuit (15), the resistive memory unit being arranged to store the state of the neuron indicated by the tank resistance and to receive the neuron input signal ( 11) For programming the tank resistance to change the neuron state, a neuron output circuit (15) for providing a neuron output signal (12) in response to the tank resistance crossing a threshold. The device (1) comprises an input signal generator (4) connected to the device input (2) and the set of neuron circuits (3) for generating a neuron input signal (11) for the set from the input data signal . The device (1) further comprises a device output circuit (5) connected to the collective neuron output circuit (15) for generating a device output signal dependent on the collective neuron output signal (12), whereby the processing device ( 1) Utilize the randomness of the assembled resistive memory cells.

Description

Background technique [0001] The present invention relates generally to neuromorphic processing devices, and more particularly, to such devices employing resistive memory cell-based neuronal circuit ensembles. [0002] Neuromorphic technologies involve computing systems inspired by the biological architecture of the nervous system. Traditional computing models based on CMOS logic and von Neumann architecture are becoming increasingly inadequate to meet the expanded processing demands of modern computer systems. It is also very inefficient in terms of power consumption and space requirements compared to biological systems. These problems have prompted a considerable amount of research work to understand the efficient computational patterns of the human brain and to create artificial cognitive systems with unprecedented computational capabilities. [0003] Neurons, along with synapses, are the basic units of computation in the brain. A neuron can integrate the input signal it ...

AI Technical Summary

Problems solved by technology

While scalable and efficient memory synapses have been explained, the concrete realization of actual artificial neurons capable of capturing most of the fundamental properties of biological neurons is more challenging.

Images