☆ 4.8 Article

Probabilistic Neural Computing with Stochastic Devices

ADVANCED MATERIALS (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Multidisciplinary Sciences

Using machine learning as a surrogate model for agent-based simulations

Claudio Angione et al.

Summary: This study compared the performance of multiple machine-learning methods for surrogate modelling in agent-based models (ABMs). The results showed that artificial neural networks (ANNs) and gradient-boosted trees outperformed Gaussian process surrogates, the most commonly used method. Using machine-learning methods for surrogate modelling in ABMs can reduce CPU time consumption and facilitate more robust sensitivity analyses.

PLOS ONE (2022)

添加到收藏夹

Article Physics, Applied

Hardware-Aware In Situ Learning Based on Stochastic Magnetic Tunnel junctions

Jan Kaiser et al.

Summary: This paper presents a hardware neural network circuit using spintronics-based neurons, which are built with stochastic magnetic tunnel junctions. The circuit can learn weights and biases in situ and mitigate device-to-device variations. It is suitable for creating standalone artificial intelligence devices capable of fast and efficient learning at the edge.

PHYSICAL REVIEW APPLIED (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

Neuromorphic scaling advantages for energy-efficient random walk computations

J. Darby Smith et al.

Summary: Neuromorphic computing is not only limited to artificial intelligence applications, it can also be used in non-cognitive computational tasks, such as Monte Carlo methods. Random walks implemented through spiking neuromorphic architectures are important for numerical computing tasks, and have wide applications in fields such as financial economics, particle physics and machine learning.

NATURE ELECTRONICS (2022)

添加到收藏夹

Article Multidisciplinary Sciences

Neural sampling machine with stochastic synapse allows brain-like learning and inference

Sourav Dutta et al.

Summary: This study introduces a novel hardware fabric that can implement a new class of stochastic neural network called Neural Sampling Machine (NSM). They demonstrate an experimental hybrid stochastic synapse composed of a ferroelectric field-effect transistor (FeFET) and a stochastic selector element. The stochastic NSM shows promising features such as weight normalization for online learning and Bayesian inferencing, accurate image classification, and uncertainty estimation.

NATURE COMMUNICATIONS (2022)

添加到收藏夹

Article Chemistry, Multidisciplinary

Nonideality-Aware Training for Accurate and Robust Low-Power Memristive Neural Networks

Dovydas Joksas et al.

Summary: In recent years, artificial neural networks have been widely used in cognitive tasks. This article introduces a nonideality-aware training method for memristor-based neural networks, which improves energy efficiency while maintaining similar accuracy.

ADVANCED SCIENCE (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

Massively parallel probabilistic computing with sparse Ising machines

Navid Anjum Aadit et al.

Summary: Solving hard problems using conventional computing architectures is slow and inefficient, but quantum computing is still in early stages. An alternative is to build domain-specific architectures with classical hardware. A sparse Ising machine is reported here, which achieves massive parallelism and is prototyped on a field-programmable gate array. It is significantly faster than standard methods by six orders of magnitude.

NATURE ELECTRONICS (2022)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Opportunities for neuromorphic computing algorithms and applications

Catherine D. Schuman et al.

Summary: This article reviews recent advances in neuromorphic computing algorithms and applications, highlighting their attractive characteristics for the future of computing. The authors also discuss opportunities for future development of algorithms and applications on these systems.

NATURE COMPUTATIONAL SCIENCE (2022)

添加到收藏夹

Article Physics, Applied

Probabilistic computing with p-bits

Jan Kaiser et al.

Summary: The article discusses a probabilistic computer based on p-bits that can accelerate randomized algorithms used in various applications, such as Bayesian networks, optimization, Ising models, and quantum Monte Carlo. A generic architecture for p-computers and simulations with thousands of p-bits are proposed to demonstrate their potential for significant speedup.

APPLIED PHYSICS LETTERS (2021)

添加到收藏夹

Article Computer Science, Hardware & Architecture

After decades of incentivizing the isolation of hardware, software, and algorithm development, the catalysts for closer collaboration are changing the paradigm

Sara Hooker

Summary: This article argues that in the field of artificial intelligence research, the success or failure of ideas is largely determined by the tools used. The choices of software and hardware have played a crucial role in early computer science history, deciding the winners and losers.

COMMUNICATIONS OF THE ACM (2021)

添加到收藏夹

Review Computer Science, Artificial Intelligence

A review of uncertainty quantification in deep learning: Techniques, applications and challenges

Moloud Abdar et al.

Summary: Uncertainty quantification (UQ) methods are essential in reducing uncertainties in optimization and decision making processes. Bayesian approximation and ensemble learning techniques are widely used types of UQ methods.

INFORMATION FUSION (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

In situ learning using intrinsic memristor variability via Markov chain Monte Carlo sampling

Thomas Dalgaty et al.

Summary: A machine learning scheme utilizing memristor variability was developed to implement Markov chain Monte Carlo sampling in a fabricated array of devices. This approach demonstrated robustness in tasks such as malignant tissue recognition, heart arrhythmia detection, and reinforcement learning, with significantly lower total energy consumption compared to traditional CMOS-based methods.

NATURE ELECTRONICS (2021)

添加到收藏夹

Article Chemistry, Multidisciplinary

Demonstration of Nanosecond Operation in Stochastic Magnetic Tunnel Junctions

Christopher Safranski et al.

Summary: Magnetic tunnel junctions operating in the superparamagnetic regime are promising for probabilistic computing and cryptography, with the device's fluctuation time-scale determining effective system speed.

NANO LETTERS (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Massively parallel ultrafast random bit generation with a chip-scale laser

Kyungduk Kim et al.

Summary: This study introduces a method for ultrafast generation of random bit streams using a single laser diode, achieving a total bit rate of 250 terabits per second with off-line postprocessing. The approach is robust, compact, energy-efficient, and has potential applications in secure communication and high-performance computation.

SCIENCE (2021)

添加到收藏夹

Article Physics, Multidisciplinary

Nanosecond Random Telegraph Noise in In-Plane Magnetic Tunnel Junctions

K. Hayakawa et al.

Summary: Analyzing and calculating the effects of random telegraph noise on in-plane easy-axis MTJs, it was found that i-MTJs can have faster RTN. Superparamagnetic i-MTJs can achieve relaxation times down to 8 ns without bias current, significantly shorter than typical p-MTJs and faster than any reported i-MTJs to date, providing new insights for developing stochastic MTJs for high-performance probabilistic computers.

PHYSICAL REVIEW LETTERS (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Assessing a Neuromorphic Platform for use in Scientific Stochastic Sampling

James B. Aimone et al.

Summary: Recent advancements in neuromorphic algorithm development have shown that neural inspired architectures can efficiently solve scientific computing problems, but the accuracy of samples generated by neuromorphic hardware needs to be verified. By using relative entropy as a verification measure, it is demonstrated that the random samples generated on Loihi are acceptable. There is a trade-off between the lower-precision random number generation of the neuromorphic platform and the algorithm's ability to represent a discrete-time Markov chain.

2021 INTERNATIONAL CONFERENCE ON REBOOTING COMPUTING (ICRC 2021) (2021)

添加到收藏夹

Article Automation & Control Systems

A Roadmap for Reaching the Potential of Brain-Derived Computing

James B. Aimone

Summary: Neuromorphic computing is an important future technology for the computing industry, but facing challenges in establishing a cohesive research community and realizing the full potential of brain-inspired computing. This requires advancement in device hardware, computing architectures, and algorithms simultaneously, which is unprecedented in the field of computing.

ADVANCED INTELLIGENT SYSTEMS (2021)

添加到收藏夹

Review Statistics & Probability

Modern Monte Carlo methods for efficient uncertainty quantification and propagation: A survey

Jiaxin Zhang

Summary: This article provides an overview of modern Monte Carlo methods such as Multilevel Monte Carlo (MLMC), Multifidelity Monte Carlo (MFMC), and Multimodel Monte Carlo method (MMMC) that address challenges in uncertainty quantification (UQ), particularly in uncertainty propagation.

WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL STATISTICS (2021)

添加到收藏夹

Article Mathematics, Applied

From biased coin to any discrete distribution

Karol Gryszka

Summary: In this note, an algorithm is introduced to generate any discrete distribution using an arbitrary coin, regardless of fairness, and supported on a countable set.

PERIODICA MATHEMATICA HUNGARICA (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Sneak, discharge, and leakage current issues in a high-dimensional 1T1M memristive crossbar

V. A. Demin et al.

JOURNAL OF COMPUTATIONAL ELECTRONICS (2020)

添加到收藏夹

Article Computer Science, Information Systems

Autonomous Probabilistic Coprocessing With Petaflips per Second

Brian Sutton et al.

IEEE ACCESS (2020)

添加到收藏夹

Review Physics, Applied

Physics for neuromorphic computing

Danijela Markovic et al.

NATURE REVIEWS PHYSICS (2020)

添加到收藏夹

Review Computer Science, Hardware & Architecture

Neural Algorithms and Computing Beyond Moore's Law

James B. Aimone

COMMUNICATIONS OF THE ACM (2019)

添加到收藏夹

Review Chemistry, Physical

Memristive crossbar arrays for brain-inspired computing

Qiangfei Xia et al.

NATURE MATERIALS (2019)

添加到收藏夹

Article Neurosciences

Hippocampal Reactivation of Random Trajectories Resembling Brownian Diffusion

Federico Stella et al.

NEURON (2019)

添加到收藏夹

Article Physics, Applied

Voltage-Controlled Spintronic Stochastic Neuron Based on a Magnetic Tunnel Junction

Jialin Cai et al.

PHYSICAL REVIEW APPLIED (2019)

添加到收藏夹

Article Multidisciplinary Sciences

Parallel programming of an ionic floating-gate memory array for scalable neuromorphic computing

Elliot J. Fuller et al.

SCIENCE (2019)

添加到收藏夹

Review Nanoscience & Nanotechnology

Stochastic Memory Devices for Security and Computing

Roberto Carboni et al.

ADVANCED ELECTRONIC MATERIALS (2019)

添加到收藏夹

Article Multidisciplinary Sciences

Integer factorization using stochastic magnetic tunnel junctions

William A. Borders et al.

NATURE (2019)

添加到收藏夹

Article Computer Science, Hardware & Architecture

Composable Probabilistic Inference Networks Using MRAM-based Stochastic Neurons

Ramtin Zand et al.

ACM JOURNAL ON EMERGING TECHNOLOGIES IN COMPUTING SYSTEMS (2019)

添加到收藏夹

Article Engineering, Electrical & Electronic

Neuro-Inspired Computing With Emerging Nonvolatile Memory

Shimeng Yu

PROCEEDINGS OF THE IEEE (2018)

添加到收藏夹

Article Engineering, Electrical & Electronic

Multiscale Co-Design Analysis of Energy, Latency, Area, and Accuracy of a ReRAM Analog Neural Training Accelerator

Matthew J. Marinella et al.

IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS (2018)

添加到收藏夹

Review Engineering, Electrical & Electronic

In-memory computing with resistive switching devices

Daniele Ielmini et al.

NATURE ELECTRONICS (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

An All-Memristor Deep Spiking Neural Computing System: A Step Toward Realizing the Low-Power Stochastic Brain

Parami Wijesinghe et al.

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE (2018)

添加到收藏夹

Review Computer Science, Information Systems

Survey on hardware implementation of random number generators on FPGA: Theory and experimental analyses

Mohammed Bakiri et al.

COMPUTER SCIENCE REVIEW (2018)

添加到收藏夹

Article Physics, Multidisciplinary

Quantum random number generators

Miguel Herrero-Collantes et al.

REVIEWS OF MODERN PHYSICS (2017)

添加到收藏夹

Article Physics, Applied

Low-Energy Truly Random Number Generation with Superparamagnetic Tunnel Junctions for Unconventional Computing

D. Vodenicarevic et al.

PHYSICAL REVIEW APPLIED (2017)

添加到收藏夹

Article Multidisciplinary Sciences

Extracting random numbers from quantum tunnelling through a single diode

Ramon Bernardo-Gavito et al.

SCIENTIFIC REPORTS (2017)

添加到收藏夹

Article Engineering, Electrical & Electronic

μRNG: A 300-950 mV, 323 Gbps/W All-Digital Full-Entropy True Random Number Generator in 14 nm FinFET CMOS

Sanu K. Mathew et al.

IEEE JOURNAL OF SOLID-STATE CIRCUITS (2016)

添加到收藏夹

Article Neurosciences

Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines

Emre O. Neftci et al.

FRONTIERS IN NEUROSCIENCE (2016)

添加到收藏夹

Article Neurosciences

Energy Scaling Advantages of Resistive Memory Crossbar Based Computation and Its Application to Sparse Coding

Sapan Agarwal et al.

FRONTIERS IN NEUROSCIENCE (2016)

添加到收藏夹

Article Multidisciplinary Sciences

Impermanence of dendritic spines in live adult CA1 hippocampus

Alessio Attardo et al.

NATURE (2015)

添加到收藏夹

Article Nanoscience & Nanotechnology

A new spin on magnetic memories

Andrew D. Kent et al.

NATURE NANOTECHNOLOGY (2015)

添加到收藏夹

Article Physics, Nuclear

EPOS LHC: Test of collective hadronization with data measured at the CERN Large Hadron Collider

T. Pierog et al.

PHYSICAL REVIEW C (2015)

添加到收藏夹

Article Multidisciplinary Sciences

Improved signaling as a result of randomness in synaptic vesicle release

Calvin Zhang et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2015)

添加到收藏夹

Article Computer Science, Hardware & Architecture

Survey of Stochastic Computing

Armin Alaghi et al.

ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS (2013)

添加到收藏夹

Article Computer Science, Theory & Methods

Graphics processing unit (GPU) programming strategies and trends in GPU computing

Andre R. Brodtkorb et al.

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING (2013)

添加到收藏夹

Article Engineering, Electrical & Electronic

Overview of Beyond-CMOS Devices and a Uniform Methodology for Their Benchmarking

Dmitri E. Nikonov et al.

PROCEEDINGS OF THE IEEE (2013)

添加到收藏夹

Article Physics, Multidisciplinary

Silicon quantum electronics

Floris A. Zwanenburg et al.

REVIEWS OF MODERN PHYSICS (2013)

添加到收藏夹

Article Computer Science, Hardware & Architecture

DARK SILICON AND THE END OF MULTICORE SCALING

Hadi Esmaeilzadeh et al.

IEEE MICRO (2012)

添加到收藏夹

Article Engineering, Electrical & Electronic

A High-Yield HfOx-Based Unipolar Resistive RAM Employing Ni Electrode Compatible With Si-Diode Selector for Crossbar Integration

X. A. Tran et al.

IEEE ELECTRON DEVICE LETTERS (2011)

添加到收藏夹

Article Biochemical Research Methods

Neural Dynamics as Sampling: A Model for Stochastic Computation in Recurrent Networks of Spiking Neurons

Lars Buesing et al.

PLOS COMPUTATIONAL BIOLOGY (2011)

添加到收藏夹

Article Computer Science, Artificial Intelligence

GPU implementation of neural networks

KS Oh et al.

PATTERN RECOGNITION (2004)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.