Probabilistic Circuits for Autonomous Learning: A simulation study

Abstract

Modern machine learning is based on powerful algorithms running on digital computing platforms and there is great interest in accelerating the learning process and making it more energy efficient. In this paper we present a fully autonomous probabilistic circuit for fast and efficient learning that makes no use of digital computing. Specifically we use SPICE simulations to demonstrate a clockless autonomous circuit where the required synaptic weights are read out in the form of analog voltages. Such autonomous circuits could be particularly of interest as standalone learning devices in the context of mobile and edge computing.

References in corpus (10)

• Deep Learning in Neural Networks: An Overview
• Stochastic p-bits for Invertible Logic
• Intrinsic optimization using stochastic nanomagnets
• Low Barrier Magnet Design for Efficient Hardware Binary Stochastic Neurons
• Scalable Emulation of Sign-Problem$-$Free Hamiltonians with Room Temperature p-bits
• Subnanosecond Fluctuations in Low-Barrier Nanomagnets
• GPU-accelerated Gibbs sampling: a case study of the Horseshoe Probit model
• Low Barrier Nanomagnet Design for Binary Stochastic Neurons: Design Challenges for Real Nanomagnets with Fabrication Defects
• Voltage-driven Building Block for Hardware Belief Networks
• Robustness and scalability of p-bits implemented with low energy barrier nanomagnets

Cited by in corpus (10)

• Probabilistic computing with p-bits
• Hardware-aware $insitu$ Boltzmann machine learning using stochastic magnetic tunnel junctions
• Stochastic Thermodynamics of Non-Linear Electronic Circuits: A Realistic Framework for Computing around kT
• Double Free-Layer Magnetic Tunnel Junctions for Probabilistic Bits
• Quantitative Evaluation of Hardware Binary Stochastic Neurons
• Hardware Design for Autonomous Bayesian Networks
• Reliability and entropy production in non-equilibrium electronic memories
• Physical Neural Networks with Self-Learning Capabilities
• Superparamagnetic and Stochastic-Write Magnetic Tunnel Junctions for High-Speed True Random Number Generation in Advanced Computing
• An improved update rule for probabilistic computers