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

The Ideal Transformer01:26

The Ideal Transformer

909
In single-phase two-winding transformers, two windings are coiled around a magnetic core characterized by cross-sectional area A and magnetic permeability μ. A phasor current i1 enters the left winding while i2 exits the right winding, establishing the fundamental working of the transformer through electromagnetic principles.
Ampere's Law forms the basis of understanding the magnetic field within the transformer. It states that the integral of the magnetic field intensity's...
909
Types Of Transformers01:16

Types Of Transformers

1.1K
Transformers can provide desired voltages to a circuit by modifying the number of turns in the secondary windings.
If the ratio of the number of turns in the secondary winding to that of the primary winding is greater than one, then the transformer is said to be a step-up transformer. In a step-up transformer, the voltage at the secondary winding is greater than the voltage applied at the primary winding.
However, if this ratio is less than one, the transformer is said to be a step-down...
1.1K
Equivalent Circuits for Practical Transformers01:28

Equivalent Circuits for Practical Transformers

807
The practical equivalent circuits of single-phase two-winding transformers exhibit significant deviations from their idealized versions due to the inherent properties of winding resistance and finite core permeability. These properties result in real and reactive power losses, affecting the transformer's performance. Understanding these deviations is crucial for designing more efficient transformers.
In a practical transformer, each winding exhibits resistance and leakage reactance. The...
807
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
Transformers with Off-Nominal Turns Ratios01:25

Transformers with Off-Nominal Turns Ratios

213
In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the...
213
Energy Losses in Transformers01:21

Energy Losses in Transformers

981
In an ideal transformer, it is assumed that there are no energy losses, and, hence, all the power at the primary winding is transferred to the secondary winding. However, in reality,  the transformers always have some energy losses, and, hence, the output power obtained at the secondary winding is less than the input power at the primary winding due to energy losses.
There are four main reasons for energy losses in transformers.
The first cause can be  the high resistance of the...
981

You might also read

Related Articles

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

Sort by
Same author

Factors associated with pulmonary embolism in children with refractory <i>Mycoplasma pneumoniae</i> pneumonia and elevated D-dimer.

Frontiers in pediatrics·2026
Same author

3-O-p-coumaroylquinic acid and 4-O-p-coumaroylquinic acid from Hemerocallis citrina Baroni exert antidepressant effects via CA/Dopa/DA/NE and PKA/CREB/BDNF signaling pathways.

NPJ science of food·2026
Same author

Associations of three metabolic biomarkers with the risk of cardiometabolic multimorbidity: a national prospective study.

Lipids in health and disease·2026
Same author

Root Plasticity and Elemental Stoichiometry Are Associated with Competitive Shifts Between <i>Azolla</i> and <i>Lemna</i> Under Different Nitrogen Levels.

Plants (Basel, Switzerland)·2026
Same author

Coimmobilized Pyridoxal 5'-Phosphate and Aminotransferase in a Hydrogen-Bonded Organic Framework for Sustainable Synthesis of Sitagliptin.

Langmuir : the ACS journal of surfaces and colloids·2026
Same author

<i>q</i> <i>orA</i> shapes organ-specific adaptation of ST59-MRSA via balancing immune evasion and metabolic trade-off.

iScience·2026

Related Experiment Video

Updated: Sep 15, 2025

Author Spotlight: Simple and Efficient Neural Retina Organoid Production for Disease Modeling
05:03

Author Spotlight: Simple and Efficient Neural Retina Organoid Production for Disease Modeling

Published on: December 22, 2023

1.4K

Perovskite Neuromorphic Engine for Transformer Architectures.

Zhenye Zhan1, Yulu Gao2,3, Yue Liao4

  • 1Siyuan Laboratory, Guangdong Provincial Engineering Technology Research Center of Vacuum Coating Technologies and New Energy Materials, Department of Physics, Jinan University, Guangzhou, Guangdong, 510632, China.

Advanced Science (Weinheim, Baden-Wurttemberg, Germany)
|July 13, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a perovskite memristive computing unit for efficient artificial neural network (ANN) hardware. It enables analog processing for Transformer ANNs, achieving high performance with significantly reduced energy consumption.

Keywords:
artificial neural networksmemristorsneuromorphic computingperovskite devices

More Related Videos

Interfacing 3D Engineered Neuronal Cultures to Micro-Electrode Arrays: An Innovative In Vitro Experimental Model
09:47

Interfacing 3D Engineered Neuronal Cultures to Micro-Electrode Arrays: An Innovative In Vitro Experimental Model

Published on: October 18, 2015

10.2K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.0K

Related Experiment Videos

Last Updated: Sep 15, 2025

Author Spotlight: Simple and Efficient Neural Retina Organoid Production for Disease Modeling
05:03

Author Spotlight: Simple and Efficient Neural Retina Organoid Production for Disease Modeling

Published on: December 22, 2023

1.4K
Interfacing 3D Engineered Neuronal Cultures to Micro-Electrode Arrays: An Innovative In Vitro Experimental Model
09:47

Interfacing 3D Engineered Neuronal Cultures to Micro-Electrode Arrays: An Innovative In Vitro Experimental Model

Published on: October 18, 2015

10.2K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.0K

Area of Science:

  • Materials Science
  • Computer Engineering
  • Neuroscience

Background:

  • Memristive computing offers efficient analog multiply-and-accumulation (MAC) operations for artificial neural networks (ANNs).
  • Current memristive approaches face inefficiencies in advanced network structures due to analog-digital data exchange.
  • Transformer ANNs, crucial for advanced AI, require complex operations that challenge existing memristive implementations.

Purpose of the Study:

  • To develop a perovskite memristive computing unit capable of performing all mathematical operations for Transformer ANNs in the analog domain.
  • To demonstrate the feasibility of a fully analog neuromorphic engine for advanced AI tasks.
  • To overcome the limitations of data conversion in current memristive computing architectures.

Main Methods:

  • Fabrication of a perovskite memristive computing unit using vapor deposition, enabling reconfigurability and nonlinearity.
  • Implementation of a prototypical attention module using memristive cells configured for dynamic MAC, activation, and softmax functions.
  • Construction and testing of a multi-layer Transformer network utilizing cascaded attention modules for real-world tasks.

Main Results:

  • The developed memristive unit successfully performed all necessary operations for Transformer ANNs in the analog domain.
  • A neuromorphic engine based on this unit achieved performance comparable to GPU acceleration on RGB-T tracking and visual question answering tasks.
  • The memristive engine demonstrated a 98.3% reduction in energy consumption (1.7% of GPU) and a 58-fold increase in power efficiency.

Conclusions:

  • The perovskite memristive computing unit offers a pathway to highly efficient and accurate hardware acceleration for advanced ANNs, particularly Transformer models.
  • Fully analog processing in memristive devices eliminates data conversion bottlenecks, paving the way for next-generation neuromorphic computing.
  • This work highlights the potential of memristive devices in realizing energy-efficient AI hardware for complex computational tasks.