Impact of Linearity and Write Noise of Analog Resistive Memory Devices in a Neural Algorithm Accelerator
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Resistive memory (ReRAM) shows promise for use as an analog synapse element in energy-efficient neural network algorithm accelerators. A particularly important application is the training of neural networks, as this is the most computationally-intensive procedure in using a neural algorithm. However, training a network with analog ReRAM synapses can significantly reduce the accuracy at the algorithm level. In order to assess this degradation, analog properties of ReRAM devices were measured and hand-written digit recognition accuracy was modeled for the training using backpropagation. Bipolar filamentary devices utilizing three material systems were measured and compared: one oxygen vacancy system, Ta-TaOx, and two conducting metallization systems, Cu-SiO2, and Ag/chalcogenide. Analog properties and conductance ranges of the devices are optimized by measuring the response to varying voltage pulse characteristics. Key analog device properties which degrade the accuracy are update linearity and write noise. Write noise may improve as a function of device manufacturing maturity, but write nonlinearity appears relatively consistent among the different device material systems and is found to be the most significant factor affecting accuracy. As a result, this suggests that new materials and/or fundamentally different resistive switching mechanisms may be required to improve device linearity and achieve higher algorithm training accuracy.
- Research Organization:
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Sandia National Lab. (SNL-CA), Livermore, CA (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)
- Grant/Contract Number:
- AC04-94AL85000
- OSTI ID:
- 1429781
- Report Number(s):
- SAND-2017-5497J; ISBN 978-1-5386-1553-9; 653576
- Journal Information:
- Conference Proceedings - IEEE International Conference on Rebooting Computing (ICRC), Vol. 2017; ISSN 2768-3354
- Publisher:
- IEEECopyright Statement
- Country of Publication:
- United States
- Language:
- English
Optimized pulsed write schemes improve linearity and write speed for low-power organic neuromorphic devices
|
journal | May 2018 |
Spiking Neural Networks Hardware Implementations and Challenges: A Survey
|
journal | April 2019 |
Analog high resistance bilayer RRAM device for hardware acceleration of neuromorphic computation
|
journal | November 2018 |
Similar Records
Optimized pulsed write schemes improve linearity and write speed for low-power organic neuromorphic devices
Training a Neural Network on Analog TaOx ReRAM Devices Irradiated With Heavy Ions: Effects on Classification Accuracy Demonstrated With CrossSim