Magnetic-Tunnel-Junction-Based Probabilistic Processor for Efficient Embodied Evolution

doi:10.1021/acs.nanolett.6c00275

2026-04-22

PRE

DOI：10.1021/acs.nanolett.6c00275

原文链接

原文求助

摘要

En 中文

In embodied artificial intelligence (AI), evolutionary search enables adaptation in complex and uncertain environments but relies on massive stochastic sampling, which in hardware is typically generated using complementary metal-oxide-semiconductor pseudorandom number generators with significant power and area costs. In this paper, we present a 256-magnetic-tunnel-junction (MTJ)-based probabilistic processor as an efficient physical platform for embodied evolution. Using an Ising-based probabilistic sampler, we experimentally construct highly reconfigurable Gaussian probabilistic bits from networks of MTJ-based probabilistic bits and scale the architecture to 256 parallel generators for evolutionary mutation. We demonstrate evolved agent morphologies comparable to those obtained using an ideal software Gaussian random number generator in a robotic locomotion task. MTJ-based stochasticity further drives on-hardware selection, including a diversity-aware scheme that balances lineage diversity and fitness. Our results establish that MTJ-based probabilistic hardware is a promising low-power stochastic substrate for embodied AI and evolutionary robotics.

Keyword:

Algorithms

Mathematical methods

Morphology

Neural networks

Optimization

embodied artificial intelligence

magnetic tunnel junctions

probabilistic computing hardware

reconfigurable random number generator

期刊

Nano Letters

IF:

9.1

论文数:

2.7W

被引数:

16.5W

机构

national university of singapore

学者数:

4.6K

论文数: 2.4K

被引数: 1

引用论文

Gaussian Random Number Generator With Reconfigurable Mean and Variance Using Stochastic Magnetic Tunnel Junctions

IEEE Magnetics Letters

IF0

2022-01-01

OAAI

Punyashloka Debashis; Hai Li; Dmitri Nikonov; Ian Young

Beyond Ising: Mixed Continuous Optimization with Gaussian Probabilistic Bits Using Stochastic MTJs

2024 IEEE International Electron Devices Meeting (IEDM)

IF0

2024-12-07

PREAI

Singh,Nihal Sanjay; Delacour,Corentin; Niazi,Shaila; Selcuk,Kemal; Golenchenko,Daniel; Kaneko,Haruna; Kanai,Shun; Ohno,Hideo; Fukami,Shunsuke; Camsari,Kerem Y.

Real-time object detection for unmanned aerial vehicles based on vision transformer and edge computing 基于视觉变换器和边缘计算的无人机实时目标检测

Scientific Reports

IF3.9

2026-01-31