Resistive processing unit

Abstract

Embodiments are directed to a two-terminal resistive processing unit (RPU) having a first terminal, a second terminal and an active region. The active region effects a non-linear change in a conduction state of the active region based on at least one first encoded signal applied to the first terminal and at least one second encoded signal applied to the second terminal. The active region is configured to locally perform a data storage operation of a training methodology based at least in part on the non-linear change in the conduction state. The active region is further configured to locally perform a data processing operation of the training methodology based at least in part on the non-linear change in the conduction state.

Description

technical field [0001] The present disclosure generally relates to novel configurations of trainable resistance crosspoint devices referred to herein as resistance processing units (RPUs). More specifically, the present disclosure relates to artificial neural networks (ANNs) formed from crossbar arrays of two-terminal RPUs that provide local data storage and local data processing without requiring additional processing elements beyond the two-terminal RPU, by This accelerates ANN learning and enables the ability to implement algorithms such as online neural network training, matrix inversion, matrix decomposition, etc. Background technique [0002] "Machine learning" is used broadly to describe the main functions of electronic systems that learn from data. In machine learning and cognitive science, artificial neural networks are a family of statistical learning models inspired by the biological neural networks of animals, especially the brain. Artificial neural networks ca...

AI Technical Summary

Problems solved by technology

[0007] Although potentially lower power consumption, performing offline training can be difficult and resource-intensive because a large number of adjustable parameters (e.g., weights) in the ANN model typically need to be modified during training to match the training data to the input-output pair

Therefore, simplifying the cross-point devices of the ANN architecture to prioritize power-saving, offline learning techniques usually means that the training speed and training efficiency are not optimized

Images