Physical Characteristics AwareEx-SituTraining Framework for Inverter-Based Memristive Neuromorphic Circuits
This is training framework for an inverter-based memristive neuromorphic hardware. The framework, which is called PHAX, is a physical characteristics aware one relying on an ex-situ training approach. The considered neuromorphic circuit is highly energy efficient hybrid CMOS-memristive implementation of neuromorphic circuits.
Usage
Start with Our_Approach.m. You must change Our_approach.m for modifing the configuration of network or loading new dataset.
Developers
Mohammand Ansari mo.ansari@ut.ac.ir
Arash Fayyazi fayyazi@usc.edu
Mehdi Kamal mehdikamal@ut.ac.ir
Ali Afzali-Kusha afzali@ut.ac.ir
Massoud Pedram pedram@usc.edu
Citation
Please cite following paper:
M. Ansari et al., "PHAX: Physical Characteristics AwareEx-SituTraining Framework for Inverter-Based Memristive Neuromorphic Circuits," in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 37, no. 8, pp. 1602-1613, Aug. 2018. doi: 10.1109/TCAD.2017.2764070
License
This framework may be freely copied and used for research purposes under the BSD 3-Clause License.
Questions or Bugs?
You may send email to fayyazi@usc.edu for any questions you may have or bugs that you find.