ECRAM as Scalable Synaptic Cell for High-Speed, Low-Power Neuromorphic Computing

  title={ECRAM as Scalable Synaptic Cell for High-Speed, Low-Power Neuromorphic Computing},
  author={Jianshi Tang and Douglas M. Bishop and Seyoung Kim and Matthew Copel and Tayfun Gokmen and Teodor K. Todorov and SangHoon Shin and Ko-Tao Lee and Paul M. Solomon and Kevin K. H. Chan and Wilfried E. Haensch and John Rozen},
  journal={2018 IEEE International Electron Devices Meeting (IEDM)},
We demonstrate a nonvolatile Electro-Chemical Random-Access Memory (ECRAM) based on lithium (Li) ion intercalation in tungsten oxide (WO3) for high-speed, low-power neuromorphic computing. Symmetric and linear update on the channel conductance is achieved using gate current pulses, where up to 1000 discrete states with large dynamic range and good retention are demonstrated. MNIST simulation based on the experimental data shows an accuracy of 96%. For the first time, high-speed programming with… Expand

Figures from this paper

Experimental measurement of ungated channel region conductance in a multi-terminal, metal oxide-based ECRAM
  • Hyunjeong Kwak, Chuljun Lee, Chaeun Lee, K. Noh, Seyoung Kim
  • Physics
  • Semiconductor Science and Technology
  • 2021
Due to the rapid progress of artificial intelligence technology based on neural networks, the amount of required computation has been increasing dramatically. To keep up with the ever-increasingExpand
A back-end, CMOS compatible ferroelectric Field Effect Transistor for synaptic weights
Voltage-controlled, symmetric and analog potentiation and depression of a ferroelectric Hf0.57Zr0.43O2 field effect transistor (FeFET) with good linearity is demonstrated, and the device concept has a great potential for the fabrication of high density, large-scale integrated arrays of artificial analog synapses. Expand
Memristive and CMOS Devices for Neuromorphic Computing
The physics and operation of CMOS-based floating-gate memory devices in artificial neural networks will be addressed and several memristive concepts will be reviewed and discussed for applications in deep neural network and spiking neural network architectures. Expand
In situ Parallel Training of Analog Neural Network Using Electrochemical Random-Access Memory
The implementation of the first in situ parallel training together with strong agreement with simulation results provides a significant advance toward developing ECRAM into larger crossbar arrays for artificial neural network accelerators, which could enable orders of magnitude improvements in energy efficiency of deep neural networks. Expand
Synaptic realizations based on memristive devices
This chapter presents an overview on the current status of synaptic circuits based on memristive devices, and reviews various implementations including the single-memristor synapse, which employs resistive switchingrandom access memory, phase-change memory and spin-transfer torque magnetic random access memory. Expand
Transient Investigation of Metal-oxide based, CMOS-compatible ECRAM
Metal-oxide based Electrochemical Random-Access Memory (MO-ECRAM) has shown unique potential as a nonvolatile element for analog in-memory computation of deep learning tasks. Using a speciallyExpand
NCPower: Power Modelling for NVM-based Neuromorphic Chip
This work systemically developed analytical models based on physical laws, and integrated NCPower, an energy consumption estimator for NVM-based neuromorphic chip, and analyzed the accuracy and energy consumption of both the traditional multi-spike based SNN and the new single- Spiking neural networks. Expand
Skyrmion-based artificial synapses for neuromorphic computing
The electrical current-induced creation, motion, detection and deletion of skyrmions in ferrimagnetic multilayers can be used to mimic the behaviour of biological synapses, providing devices that could be used for neuromorphic computing tasks such as pattern recognition. Expand
Resistive switching materials for information processing
The rapid increase in information in the big-data era calls for changes to information-processing paradigms, which, in turn, demand new circuit-building blocks to overcome the decreasingExpand
A Compact Gated-Synapse Model for Neuromorphic Circuits
  • Alexander Jones, R. Jha
  • Computer Science
  • IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
  • 2021
The behavioral theory of the model is described in detail along with a full list of the default parameter settings, and the model's validity is shown via extensive simulation and fitting to experimentally reported data on published gated-synapses. Expand