| Title: |
The logarithmic memristor-based Bayesian machine |
| Authors: |
Turck, Clément; Harabi, Kamel-Eddine; Pontlevy, Adrien; Ballet, Théo; Hirtzlin, Tifenn; Vianello, Elisa; Laurent, Raphaël; Droulez, Jacques; Bessière, Pierre; Bocquet, Marc; Portal, Jean-Michel; Querlioz, Damien |
| Contributors: |
Centre de Nanosciences et de Nanotechnologies (C2N); Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS); Commissariat à l'énergie atomique et aux énergies alternatives - Laboratoire d'Electronique et de Technologie de l'Information (CEA-LETI); Direction de Recherche Technologique (CEA) (DRT (CEA)); Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA); Département Composants Silicium (DCOS); Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Direction de Recherche Technologique (CEA) (DRT (CEA)); HawAI.tech; Institut des Systèmes Intelligents et de Robotique (ISIR); Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS); Institut des Matériaux, de Microélectronique et des Nanosciences de Provence (IM2NP); Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS); This work was supported by the European Research Council starting grant NANOINFER (reference: 715872). It also benefits from France 2030 government grants managed by the French National Research Agency (ANR-22-PEEL-0010 and ANR-22-PEEL-0013) and the support of the cleanroom RENATECH network. The authors would like to thank M. Faix, R. Frisch, E. Mazer, A. Renaudineau, and J. Simatic for their discussion and invaluable feedback. Parts of this manuscript were revised with the assistance of a large language model (OpenAI ChatGPT).; ANR-22-PEEL-0010,BEP,BioElectronPhoton(2022); ANR-22-PEEL-0013,CHOOSE,Co-optimisation tecHnOlOgie, deSign, systèmEs : benchmarking and roadmapping of emerging technologies(2022); European Project: 715872,ERC-2016-STG,ERC-2016-STG,NANOINFER(2017) |
| Source: |
EISSN: 2731-3395 ; Communications Engineering ; https://hal.science/hal-05357635 ; Communications Engineering, 2025, 4 (1), pp.35. ⟨10.1038/s44172-025-00360-2⟩ |
| Publisher Information: |
CCSD; Nature |
| Publication Year: |
2025 |
| Subject Terms: |
[PHYS]Physics [physics]; [SPI]Engineering Sciences [physics] |
| Description: |
International audience ; The demand for explainable and energy-efficient artificial intelligence (AI) systems for edge computing has led to growing interest in electronic systems dedicated to Bayesian inference. Traditional designs of such systems often rely on stochastic computing, which offers high energy efficiency but suffers from latency issues and struggles with low-probability values. Here, we introduce the logarithmic memristor-based Bayesian machine, an innovative design that leverages the unique properties of memristors and logarithmic computing as an alternative to stochastic computing. We present a prototype machine fabricated in a hybrid CMOS/hafnium-oxide memristor process. We validate the versatility and robustness of our system through experimental validation and extensive simulations in two distinct applications: gesture recognition and sleep stage classification. The logarithmic approach simplifies the computational model by converting multiplications into additions and enhances the handling of low-probability events, which are crucial in time-dependent tasks. Our results demonstrate that the logarithmic Bayesian machine achieves superior performance in terms of accuracy and energy efficiency compared to its stochastic counterpart, particularly in scenarios involving complex probabilistic models. This approach enables the development of energy-efficient and reliable AI systems for edge devices. |
| Document Type: |
article in journal/newspaper |
| Language: |
English |
| Relation: |
https://doi.org/10.5281/zenodo.2650142; info:eu-repo/semantics/altIdentifier/arxiv/2406.03492; info:eu-repo/grantAgreement//715872/EU/Intelligent Memories that Perform Inference with the Physics of Nanodevices/NANOINFER; ARXIV: 2406.03492 |
| DOI: |
10.1038/s44172-025-00360-2 |
| Availability: |
https://hal.science/hal-05357635; https://hal.science/hal-05357635v1/document; https://hal.science/hal-05357635v1/file/s44172-025-00360-2.pdf; https://doi.org/10.1038/s44172-025-00360-2 |
| Rights: |
https://creativecommons.org/licenses/by-nc-nd/4.0/ ; info:eu-repo/semantics/OpenAccess |
| Accession Number: |
edsbas.95EEDF59 |
| Database: |
BASE |