IP Library › Granted Patent US 12,725,016
Granted Patent B2
US 12,725,016 · App. 16/530,714 · Granted Sep 1, 2026

Reconfigurable FinFET-based artificial neuron and synapse devices

Inventor: Milan Pesic (Berlin, DE)
Assignee: Applied Materials, Inc.
G06N3/063G06N3/065
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,725,016
App. No.
16/530,714
Granted
Sep 1, 2026
Kind
B2
Abstract

A semiconductor device that implements artificial neurons and synapses together on the semiconductor device includes a plurality of fins formed on the semiconductor device, and a plurality of gates formed around the plurality of fins to form a plurality of fin field-effect transistors (FinFETs). The plurality of FinFETs may form one or more artificial synapses and one or more artificial neurons. Each of the one or more artificial synapses may include two or more of the plurality of gates. Each of the one or more artificial neurons comprises one of the plurality of gates.

Claims (37)

1 . A semiconductor device that implements artificial neurons and synapses together on the semiconductor device, the semiconductor device comprising:

a plurality of fins formed on the semiconductor device;

a plurality of gates formed around the plurality of fins to form a plurality of fin field-effect transistors (FinFETs), wherein:

the plurality of FinFETs comprise one or more artificial synapses and one or more artificial neurons;

each of the one or more artificial synapses comprises two or more of the plurality of gates that are conductively connected together; and

each of the one or more artificial neurons comprises one of the plurality of gates.

2 . The semiconductor device of claim 1 , further comprising:

one or more connections between the plurality of gates, wherein the one or more connections form a network of the one or more artificial synapses and the one or more artificial neurons.

3 . The semiconductor device of claim 2 , wherein the one or more connections between the plurality of gates are implemented directly after gate deposition.

4 . The semiconductor device of claim 2 , wherein the one or more connections between the plurality of gates are implemented in a metal layer of the semiconductor device.

5 . The semiconductor device of claim 1 , wherein:

the plurality of fins comprises a first fin;

the plurality of gates comprises a first plurality of gates; and

the first plurality of gates is formed over the first fin to form a single one of the one or more artificial synapses.

6 . The semiconductor device of claim 1 , wherein:

the plurality of fins comprises a first plurality of fins;

the plurality of gates comprises a first gate; and

the first gate is formed over the first plurality of fins to form at least a portion of one of the one or more artificial synapses.

7 . The semiconductor device of claim 1 , wherein the semiconductor device comprises a silicon substrate, and each of the plurality of fins is formed as a vertical ridge in the silicon substrate.

8 . The semiconductor device of claim 1 , wherein the plurality of finFETs comprises a plurality of ferroelectric finFETs, wherein the two or more of the plurality of gates form two or more ferroelectric domains that switch independently in response to pulses received by a corresponding artificial synapse.

9 . The semiconductor device of claim 1 , wherein the plurality of fins is formed in a uniform pattern on the semiconductor device, such that each of the plurality of fins can be used for one of the one or more artificial neurons or one of the one or more artificial synapses.

10 . The semiconductor device of claim 1 , wherein each of the plurality of fins is formed to have a uniform width.

11 . A method of implementing artificial neurons and synapses together on a semiconductor device, the method comprising:

forming a plurality of fins on the semiconductor device;

forming a plurality of gates around the plurality of fins to form a plurality of fin field-effect transistors (FinFETs), wherein:

the plurality of FinFETs comprise one or more artificial synapses and one or more artificial neurons;

each of the one or more artificial synapses comprises two or more of the plurality of gates that are conductively connected together; and

each of the one or more artificial neurons comprises one of the plurality of gates.

12 . The method of claim 11 , further comprising making one or more connections between the plurality of gates, wherein the one or more connections form a network of the one or more artificial synapses and the one or more artificial neurons.

13 . The method of claim 12 , wherein the one or more connections are made in a system level after fabricating the semiconductor device.

14 . The method of claim 12 , wherein the one or more connections are made in a software level after fabricating the semiconductor device.

15 . The method of claim 11 , wherein each of the one or more artificial neurons is configured to receive a plurality of signal pulses before switching between conductivity states.

16 . The method of claim 11 , wherein each of the one or more artificial synapses is configured to receive a plurality of signal pulses, each of which cause respective domains to switch between conductivity states.

17 . The method of claim 11 , wherein each of the plurality of fins is 10 nm wide.

18 . The method of claim 11 , wherein the plurality of fins and the plurality of gates are formed in a plurality of discrete fields as neurons, and ones of the plurality of discrete fields are connected to form synapses.

19 . The method of claim 11 , wherein the plurality of fins and the plurality of gates are formed in a same technology node.

20 . The method of claim 11 , further comprising forming one or more complimentary metal-oxide silicon (CMOS) circuits on the semiconductor device.

Assignments (2)
CORRECTIVE ASSIGNMENT TO CORRECT THE RECEIVING PARTY NAME PREVIOUSLY RECORDED AT REEL: 50038 FRAME: 518. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT . Recorded Apr 22, 2026
From: PESIC, MILAN
To: APPLIED MATERIALS, INC.
Reel/Frame 075446/0069 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 13, 2019
From: PESIC, MILAN
To: APPLIED MATERIALS, INC
Reel/Frame 050038/0518 →
Continuity (1)
Related Publication 20210034953A1 · Feb 4, 2021
References Cited (47)
US 8719759B1 · Chou · 2014 [cited by examiner]
US 20010015450A1 · Sugibayashi et al. · 2001 [cited by applicant]
US 20070247906A1 · Watanabe et al. · 2007 [cited by applicant]
US 20130141963A1 · Liaw · 2013 [cited by applicant]
US 20140122402A1 · Bichler · 2014 [cited by examiner]
US 20140199849A1 · Mani et al. · 2014 [cited by applicant]
US 20150100532A1 · Yamaguchi · 2015 [cited by applicant]
US 20150286766A1 · Singh · 2015 [cited by examiner]
US 20170063351A1 · Kurokawa · 2017 [cited by examiner]
US 20170193363A1 · Lee · 2017 [cited by examiner]
US 20180012123A1 · Han · 2018 [cited by examiner]
US 20180211350A1 · Wang et al. · 2018 [cited by applicant]
US 20190012593A1 · Obradovic · 2019 [cited by examiner]
US 20190088329A1 · Tiwari · 2019 [cited by examiner]
US 20190108433A1 · Hsu · 2019 [cited by examiner]
US 20190180174A1 · Koswatta · 2019 [cited by examiner]
US 20190251430A1 · Gokmen · 2019 [cited by examiner]
US 20190312108A1 · Li · 2019 [cited by examiner]
US 20200042665A1 · Lin · 2020 [cited by examiner]
US 20200065647A1 · Mulaosmanovic · 2020 [cited by examiner]
US 20200364548A1 · Chang · 2020 [cited by examiner]
US 20230268396A1 · Li · 2023 [cited by examiner]
JP 2001230326A · 2001 [cited by applicant]
JP 2007266209A · 2007 [cited by applicant]
JP 2015072610A · 2015 [cited by applicant]
KR 1020130138052A · 2013 [cited by applicant]
KR 20190005101A · 2019 [cited by applicant]
WO 2018138603A1 · 2018 [cited by applicant]
WO WO2019066959A1 · 2019 [cited by examiner]
Yurchuk, Ekaterina, et al. “Charge-trapping phenomena in HfO 2-based FeFET-type nonvolatile memories.” IEEE Transactions on Electron Devices 63.9 (2016): 3501-3507. (Year: 2016). [cited by examiner]
Hoffmann, Michael, et al. “Direct observation of negative capacitance in polycrystalline ferroelectric HfO2.” Advanced Functional Materials 26.47 (2016): 8643-8649. (Year: 2016). [cited by examiner]
Pesic, Milan, et al. “Deconvoluting charge trapping and nucleation interplay in FeFETs: Kinetics and Reliability.” 2018 IEEE International Electron Devices Meeting (IEDM). IEEE, 2018: 25.1.1-25.1.4 (Year: 2018). [cited by examiner]
Du, Yuan, et al. “An analog neural network computing engine using CMOS-compatible charge-trap-transistor (CTT).” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 38.10 (2018): 1811-1819. (Ye… [cited by examiner]
Chen, Gregory K., et al. “A 4096-neuron 1M-synapse 3.8-pJ/SOP spiking neural network with on-chip STDP learning and sparse weights in 10-nm FinFET CMOS.” IEEE Journal of Solid-State Circuits 54.4 (2018): 992-1002. (Year… [cited by examiner]
Pešić, M., et al. “Physical and circuit modeling of HfO 2 based ferroelectric memories and devices.” 2017 IEEE SOI-3D-Subthreshold Microelectronics Technology Unified Conference (S3S). IEEE, 2017. (Year: 2017). [cited by examiner]
Auth, Chris, et al. “A 10nm high performance and low-power CMOS technology featuring 3 rd generation FinFET transistors, Self-Aligned Quad Patterning, contact over active gate and cobalt local interconnects.” 2017 IEEE … [cited by examiner]
Jerry, Matthew, et al. “Ferroelectric FET analog synapse for acceleration of deep neural network training.” 2017 IEEE international electron devices meeting (IEDM). IEEE, 2017: 6.2.1-6.2.4 (Year: 2017). [cited by examiner]
Wang, Zheng, et al. “Experimental Demonstration of Ferroelectric Spiking Neurons for Unsupervised Clustering.” 2018 IEEE International Electron Devices Meeting (IEDM). 2018. (Year: 2018). [cited by examiner]
Chen, C., et al. “Bio-inspired neurons based on novel leaky-FeFET with ultra-low hardware cost and advanced functionality for all-ferroelectric neural network.” 2019 Symposium on VLSI Technology. IEEE, Jun. 2019: T136-T… [cited by examiner]
Seo, Myungsoo, et al. “First demonstration of a logic-process compatible junctionless ferroelectric FinFET synapse for neuromorphic applications.” IEEE Electron Device Letters 39.9 (2018): 1445-1448. (Year: 2018). [cited by examiner]
Kim, Hyungjin, et al. “Silicon-based floating-body synaptic transistor with frequency-dependent short-and long-term memories.” IEEE Electron Device Letters 37.3 (2016): 249-252. (Year: 2016). [cited by examiner]
International Preliminary Report on Patentability mailed on Feb. 17, 2022 in International Patent Application No. PCT/US2020/043796, 5 pages. [cited by applicant]
International Search Report and Written Opinion mailed Nov. 9, 2020 in International Patent Application No. PCT/US2020/043796, 9 pages. [cited by applicant]
Chatterjee, et al. “A CMOS Compatible Bulk FinFET-Based Ultra Low Energy Leaky Integrate and Fire Neuron for Spiking Neural Networks”, IEEE Electron Device Letters. vol. 40, No. 8, Aug. 2019, pp. 1-4. DOI. 10.1109/LED.2… [cited by applicant]
“Intel Announces Production-Ready 22nm 3-D Tri-Gate Transistor” [Web page], May 5, 2011, Retrieved on Aug. 6, 2023 from Coventor website: https://www.coventor.com/blog/intel-announces-production-ready-22nm-3-d-tri-gate-… [cited by applicant]
Kentastophe (https://electronics.stackexchange.com/users/166306/kentastophe), “Multiple Transistors (FinFET) sharing a gate?,” Retrieved on Aug. 6, 2023 from https://electronics.stackexchange.com/q/335397, 4 pages. [cited by applicant]
Extended European Search Report mailed Jul. 21, 2023 in European Application No. 20850352.4, 13 pages. [cited by applicant]