Journal
NATURE COMMUNICATIONS
Volume 12, Issue 1, Pages -Publisher
NATURE PORTFOLIO
DOI: 10.1038/s41467-021-24427-8
Keywords
-
Categories
Funding
- IITD-FIRP grant [SERB-CRG/2018/001901]
- CYRAN AI Solutions
- NET-JRF Fellowship of UGC
Ask authors/readers for more resources
Researchers have proposed a Double EXponential Adaptive Threshold (DEXAT) neuron model and an efficient hardware implementation that demonstrates high classification accuracy across various datasets. Additionally, they have explored the impact of nanodevice variability and endurance on the robustness of this model and its implementation.
We propose a Double EXponential Adaptive Threshold (DEXAT) neuron model that improves the performance of neuromorphic Recurrent Spiking Neural Networks (RSNNs) by providing faster convergence, higher accuracy and a flexible long short-term memory. We present a hardware efficient methodology to realize the DEXAT neurons using tightly coupled circuit-device interactions and experimentally demonstrate the DEXAT neuron block using oxide based non-filamentary resistive switching devices. Using experimentally extracted parameters we simulate a full RSNN that achieves a classification accuracy of 96.1% on SMNIST dataset and 91% on Google Speech Commands (GSC) dataset. We also demonstrate full end-to-end real-time inference for speech recognition using real fabricated resistive memory circuit based DEXAT neurons. Finally, we investigate the impact of nanodevice variability and endurance illustrating the robustness of DEXAT based RSNNs. Recurrent spiking neural networks have garnered interest due to their energy efficiency; however, they suffer from lower accuracy compared to conventional neural networks. Here, the authors present an alternative neuron model and its efficient hardware implementation, demonstrating high classification accuracy across a range of datasets.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available