Spintronic Stochastic Neuron-Based Deep Belief Networks for Image Classification
Spintronic devices hold promise for AI, particularly in Boltzmann computing architectures, due to their tunable stochastic switching. We demonstrate a SOT-tuned spintronic neuron integrated into a deep belief network for pattern classification. Its switching probability, driven by current, mirrors biological neuron activation through a sigmoid function. Integrated with RBM and logistic regression, the network achieves 97% classification accuracy, stable across temperature variations, underscoring spintronics' potential in robust AI applications.
Authors
- Hossein Fariborzi (ORCID: https://orcid.org/0000-0002-7828-0239)
- Divyanshu Divyanshu
- Selma Amara (ORCID: https://orcid.org/0000-0002-0131-1703)
- Camelia Florina Florica (ORCID: https://orcid.org/0009-0001-9983-9572)
- Meng Tang (ORCID: https://orcid.org/0009-0002-6276-4738)
- Gianluca Setti (ORCID: https://orcid.org/0000-0002-2496-1856)
- Aijaz H. Lone (ORCID: https://orcid.org/0000-0002-1687-2917)
- Daniel N. Rahimi (ORCID: https://orcid.org/0009-0009-7869-1116)
Institutions
- King Abdullah University of Science and Technology (SA)
Publication Details
- Published
- 2025-03-09
- DOI
- https://doi.org/10.1109/edtm61175.2025.11041293
- Primary Topic
- Neural Networks and Reservoir Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00