Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Atomic Nuclei: Nuclear Spin State Overview01:03

Atomic Nuclei: Nuclear Spin State Overview

1.2K
NMR-active nuclei have energy levels called 'spin states' that are associated with the orientations of their nuclear magnetic moments. In the absence of a magnetic field, the nuclear magnetic moments are randomly oriented, and the spin states are degenerate. When an external magnetic field is applied, the spin states have only 2 + 1 orientations available to them. A proton with = ½ has two available orientations. Similarly, for a quadrupolar nucleus with a nuclear spin value of...
1.2K
The Role of Ion Channels in Neuronal Computation01:19

The Role of Ion Channels in Neuronal Computation

3.3K
A postsynaptic neuron usually receives numerous impulses from several other presynaptic neurons. The axon hillock of the postsynaptic neuron integrates all these signals and determines the likelihood of firing an action potential.
Sometimes a single EPSP is strong enough to induce an action potential in the postsynaptic neuron. However, multiple presynaptic inputs must often create EPSPs around the same time for the postsynaptic neuron to be sufficiently depolarized to fire an action potential....
3.3K
Neural Circuits01:25

Neural Circuits

1.6K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.6K
Atomic Nuclei: Nuclear Spin State Population Distribution01:14

Atomic Nuclei: Nuclear Spin State Population Distribution

1.2K
Near absolute zero temperatures, in the presence of a magnetic field, the majority of nuclei prefer the lower energy spin-up state to the higher energy spin-down state. As temperatures increase, the energy from thermal collisions distributes the spins more equally between the two states. The Boltzmann distribution equation gives the ratio of the number of spins predicted in the spin −½ (N−) and spin +½ (N+) states.
1.2K
Atomic Nuclei: Nuclear Spin01:08

Atomic Nuclei: Nuclear Spin

3.2K
All atomic particles possess an intrinsic angular momentum, or 'spin'. Electrons, protons, and neutrons each have a spin value of ½, although protons and neutrons in nuclei may have higher half-integer spins owing to energetic factors.
Atomic nuclei have a net nuclear spin, , which can have an integer or half-integer value. In atomic nuclei, the spins of protons are paired against each other but not with neutrons, and vice versa. Consequently, an even number of protons does not...
3.2K
Spin–Spin Coupling Constant: Overview01:08

Spin–Spin Coupling Constant: Overview

1.0K
In bromoethane, the three methyl protons are coupled to the two methylene protons that are three bonds away. In accordance with the n+1 rule, the signal from the methyl protons is split into three peaks with 1:2:1 relative intensities. The methylene protons appear as a quartet, with the relative intensities of 1:3:3:1.
Qualitatively, any spin plus-half nucleus polarizes the spins of its electrons to the minus-half state. Consequently, the paired electron in the hydrogen–carbon bond must...
1.0K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Coherent quantum control of nitrogen vacancy spin with nanoscale magnets.

Nature communications·2026
Same author

Strain Mediated Voltage Control of Magnetic Anisotropy and Magnetization Reversal in Bismuth-Substituted Yttrium Iron Garnet Films and Mesostructures.

ACS applied materials & interfaces·2025
Same author

Magneto-Ionic Physical Reservoir Computing in Perpendicularly Magnetized Heterostructures.

Nano letters·2025
Same author

Self-assembled 3D Interconnected Magnetic Nanowire Networks for Neuromorphic Computing.

ACS applied materials & interfaces·2025
Same author

Antiferromagnetic skyrmion-based energy-efficient leaky integrate and fire neuron device.

Nanotechnology·2025
Same author

Electrically Controlled All-Antiferromagnetic Tunnel Junctions on Silicon with Large Room-Temperature Magnetoresistance.

Advanced materials (Deerfield Beach, Fla.)·2024
Same journal

AFM-Modified Graphene Field-Effect Transistor for Sensitive Detection of Cardiac Troponin I.

Nanotechnology·2026
Same journal

Ultra-Sensitive UV Photodetectors Enabled by Built-in Electric Fields in Hierarchical NP-Type Porous Silicon.

Nanotechnology·2026
Same journal

Effect of sintering temperature on structural, microstructural and magnetic properties of La<sub>0.8</sub>Sr<sub>0.2</sub>MnO<sub>3</sub>: Evolution of faceting and terrace like morphology.

Nanotechnology·2026
Same journal

Engineered V2C MXene Anchored Cu Nanoparticles for Selective Nitrate/Nitrite Sensing and Magneto-Electrocatalytic Hydrogen Evolution Reaction.

Nanotechnology·2026
Same journal

Quantitative Mechanism Separation of Single-Event Transients in Nanosheet Transistors via TCAD Simulation.

Nanotechnology·2026
Same journal

Antibacterial, mechanical and curing properties of PMMA bone cement loaded with copper nanoparticles.

Nanotechnology·2026
See all related articles

Related Experiment Video

Updated: Sep 19, 2025

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

671

Quantized artificial neural networks implemented with spintronic stochastic computing.

Saadi Sabyasachi1, Walid Al Misba1, Yixin Shao2

  • 1Department of Mechanical and Nuclear Engineering, Virginia Commonwealth University, Richmond, VA 23284, United States of America.

Nanotechnology
|June 8, 2025
PubMed
Summary
This summary is machine-generated.

Quantized stochastic computing (SC) using stochastic-magnetic tunnel junctions (s-MTJs) significantly reduces energy consumption and latency in artificial neural networks (ANNs) while maintaining high accuracy. This approach optimizes resource-intensive matrix vector multiplications for efficient hardware implementation.

Keywords:
deep neural networksmagnetic tunnel junctions (MTJ)quantizationstochastic computing

More Related Videos

Silicon Metal-oxide-semiconductor Quantum Dots for Single-electron Pumping
14:58

Silicon Metal-oxide-semiconductor Quantum Dots for Single-electron Pumping

Published on: June 3, 2015

14.9K
Nanofabrication of Gate-defined GaAs/AlGaAs Lateral Quantum Dots
15:47

Nanofabrication of Gate-defined GaAs/AlGaAs Lateral Quantum Dots

Published on: November 1, 2013

16.4K

Related Experiment Videos

Last Updated: Sep 19, 2025

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

671
Silicon Metal-oxide-semiconductor Quantum Dots for Single-electron Pumping
14:58

Silicon Metal-oxide-semiconductor Quantum Dots for Single-electron Pumping

Published on: June 3, 2015

14.9K
Nanofabrication of Gate-defined GaAs/AlGaAs Lateral Quantum Dots
15:47

Nanofabrication of Gate-defined GaAs/AlGaAs Lateral Quantum Dots

Published on: November 1, 2013

16.4K

Area of Science:

  • * Computer Science
  • * Electrical Engineering
  • * Materials Science

Background:

  • * Artificial neural network (ANN) inference demands substantial energy and device resources due to matrix vector multiplications.
  • * Stochastic computing (SC) offers a promising, less resource-intensive alternative for ANNs, utilizing random number generators (RNGs).
  • * Stochastic-magnetic tunnel junctions (s-MTJs) can generate random bitstreams for hardware-based SC, but prior work focused on analog weights.

Purpose of the Study:

  • * To investigate the efficacy of SC for matrix vector multiplication with quantized synaptic weights and outputs.
  • * To evaluate the performance of a quantized SC-ANN using experimental s-MTJ bitstreams and discrete weight/node states.
  • * To compare the energy consumption, latency, and accuracy of quantized SC-ANNs against analog implementations.

Main Methods:

  • * Implemented quantized SC-ANNs with 5 and 11 discrete states for weights and hidden layer nodes.
  • * Utilized experimentally obtained s-MTJ bitstreams with varying lengths (100-500 bits).
  • * Trained and performed inference on the MNIST dataset using neural networks with one and three hidden layers.

Main Results:

  • * Quantized SC-ANNs demonstrated reduced latency (9×) and energy consumption (2.6×) compared to analog s-MTJ ANNs.
  • * Training with SC consistently improved accuracy across all configurations.
  • * Peak accuracy of 96.82% was achieved with a 400-bit stochastic bitstream and three hidden layers.

Conclusions:

  • * Quantized SC-ANNs effectively reduce hardware resource requirements and improve energy efficiency.
  • * The use of discrete quantized states in SC-ANNs preserves accuracy while enhancing performance.
  • * This approach offers a viable path for energy-efficient, high-performance ANNs implemented with s-MTJs.