journal article·2025-11-12

Dendritic Computing with Multigate Ferroelectric Field-Effect Transistors

A. N. M. Nafiul Islam, Xuezhong Niu, Jiahui Duan, Shubham Kumar, Kai Ni, Abhronil Sengupta

Nano Letters· Volume 25· Issue 45
Publisher page

Abstract

Although inspired by neuronal systems in the brain, artificial neural networks generally employ point-neurons, which offer computational complexity far less than that of their biological counterparts. Neurons have dendritic arbors that connect to different sets of synapses and offer local nonlinear accumulation - playing a pivotal role in processing and learning. Inspired by this, we propose a novel neuron design based on a multigate ferroelectric field-effect transistor that mimics dendrites. It leverages ferroelectric nonlinearity for local computations within dendritic branches while utilizing the transistor action to generate the neuronal output. The branched architecture enables smaller crossbar arrays in hardware integration, improving efficiency. Using an experimentally calibrated device-circuit-algorithm cosimulation framework, we demonstrate that networks incorporating our dendritic neurons achieve superior performance compared to much larger networks without dendrites (∼ 17× fewer trainable weight parameters). These findings suggest that dendritic hardware can significantly improve computational efficiency and learning capacity of neuromorphic systems optimized for edge applications.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Ferroelectric and Negative Capacitance Devices · Advanced Memory and Neural Computing · Neural Networks and Reservoir Computing

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Electrical Engineering & Computer Science

The Pennsylvania State University

Department of Electrical Engineering

University of Notre Dame

Funding

Basic Energy Sciences · National Science Foundation

References (37)

Show source-provided references
1. 10.1007/BF0247825910.1007/BF02478259 ↗
3. 10.1016/S0896-6273(01)00252-510.1016/S0896-6273(01)00252-5 ↗
4. 10.1073/pnas.80.9.279910.1073/pnas.80.9.2799 ↗
5. 10.1016/S0896-6273(03)00149-110.1016/S0896-6273(03)00149-1 ↗
6. 10.1016/j.neuron.2009.02.02110.1016/j.neuron.2009.02.021 ↗
7. 10.1038/s41467-019-11537-710.1038/s41467-019-11537-7 ↗
8. 10.1109/ISCAS.2014.686571510.1109/ISCAS.2014.6865715 ↗
9. Wu X. · Advances in neural information processing systems · 2018 · 31 · 8068
10. 10.1162/neco_a_0139010.1162/neco_a_01390 ↗
11. 10.1002/tee.2351310.1002/tee.23513 ↗
12. 10.1109/JAS.2023.12397810.1109/JAS.2023.123978 ↗
13. 10.1038/s41467-025-56297-910.1038/s41467-025-56297-9 ↗
14. Liu C. · Advances in Neural Information Processing Systems · 2024 · 37 · 79325
15. 10.1038/s41565-020-0722-510.1038/s41565-020-0722-5 ↗
16. 10.1021/acs.nanolett.4c0073910.1021/acs.nanolett.4c00739 ↗
17. 10.1038/s41467-024-48315-z10.1038/s41467-024-48315-z ↗
18. 10.1038/s41586-022-05340-610.1038/s41586-022-05340-6 ↗
19. Chen H. J.-Y. · International Electron Devices Meeting (IEDM). · 2023 · 2023 · 1
20. 10.1109/ISCAS58744.2024.10557895.10.1109/ISCAS58744.2024.10557895. ↗
21. 10.1109/TBCAS.2013.228261610.1109/TBCAS.2013.2282616 ↗
22. 10.1109/TNNLS.2016.258251710.1109/TNNLS.2016.2582517 ↗
23. 10.1109/LED.2022.318762410.1109/LED.2022.3187624 ↗
24. Deng S. · International Electron Devices Meeting (IEDM). · 2022 · 2022 · 36
25. 10.1021/acsami.1c0871810.1021/acsami.1c08718 ↗
26. 10.1109/TED.2022.314223910.1109/TED.2022.3142239 ↗
27. 10.1063/5.006486010.1063/5.0064860 ↗
28. 10.1063/5.013224210.1063/5.0132242 ↗
29. 10.1109/16.13732510.1109/16.137325 ↗
30. 10.1109/VLSITechnology18217.2020.926501410.1109/VLSITechnology18217.2020.9265014 ↗
31. 10.1109/TED.2019.292226810.1109/TED.2019.2922268 ↗
32. Jain, S.; Sengupta, A.; Roy, K.; Raghunathan, A. Rx-Caffe: Framework for evaluating and training Deep Neural Networks on Resistive Crossbars. arXiv , 2018, arXiv:1809.00072.
33. Xiao, H.; Rasul, K.; Vollgraf, R. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv , 2017, arXiv:1708.07747.
34. Hur J. · IEEE International Electron Devices Meeting (IEDM). · 2020 · 2020 · 39
35. 10.1002/aelm.20210042010.1002/aelm.202100420 ↗
36. 10.1063/1.505070010.1063/1.5050700 ↗
37. 10.1039/D0NR02204G10.1039/D0NR02204G ↗