Kim Taeyueb Park, HeeGyum Han, Ki-Hyuk Nah, Young-Jun 구현철 민병철 홍석민 Lee, Ouk Jae 2024-01-12T03:01:32Z 2024-01-12T03:01:32Z 2022-08-04 2022-07 2158-3226 https://pubs.kist.re.kr/handle/201004/76666 https://aip.scitation.org/doi/full/10.1063/5.0090577 A binary stochastic neuron (BSN) or a probabilistic bit (p-bit) randomly fluctuates between digitized "0" and "1" with a controllable functionality of time-averaged value. Such an unconventional bit is the most essential building block for the recently proposed stochastic neural networks and probabilistic computing. Here, we experimentally implement a magnetic tunnel junction (MTJ) for BSN, with relaxation times on the order of tens of milliseconds that can be modulated by a current-induced spin-transfer torque. The NIST Statistical Test Suite (800-22a) is used to verify true random number generation by the BSN-MTJ device. Our results suggest the possibility of using the artificial BSN MTJ device in neuromorphic applications as well as in a recently proposed probabilistic computing. (c) 2022 Author(s). English American Institute of Physics Inc. Demonstration of in-plane magnetized stochastic magnetic tunnel junction for binary stochastic neuron Article 10.1063/5.0090577 1 AIP Advances, v.12, no.7, pp.1 - 6 AIP Advances 12 7 1 6 Y scie scopus 000884502800008 Nanoscience & Nanotechnology Materials Science, Multidisciplinary Physics, Applied Science & Technology - Other Topics Materials Science Physics Article