• Latest
  • Trending
  • All
  • Capacitors
  • Resistors
  • Inductors
  • Filters
  • Fuses
  • Non-linear Passives
  • Applications
  • Integrated Passives
  • Oscillators
  • Passive Sensors
  • New Technologies
  • Aerospace & Defence
  • Automotive
  • Industrial
  • Market & Supply Chain
  • Medical
  • RF & Microwave
  • Telecommunication

Memristors power quick-learning neural network

26.12.2017

Resonant MLCC OBC Application Guide

2.10.2023

Bourns Releases New Compact Size High Current Ferrite Beads

2.10.2023

Skeleton Demonstrated Supercapacitor Based Shuttle Charging in Seconds

2.10.2023

NICHICON SLB Small Lithium-Titanate Rechargeable Batteries

2.10.2023

Skeleton Unveils the Leipzig Supercapacitor Factory

29.9.2023

Snubber Capacitors in Power Electronics

27.9.2023
  • Home
  • Privacy Policy
  • EPCI Membership & Advertisement
  • About
No Result
View All Result
NEWSLETTER
Passive Components Blog
  • Home
  • NewsFilter
    • All
    • Aerospace & Defence
    • Antenna
    • Applications
    • Automotive
    • Capacitors
    • Circuit Protection Devices
    • Filters
    • Fuses
    • Inductors
    • Industrial
    • Integrated Passives
    • Market & Supply Chain
    • Medical
    • New Materials & Supply
    • New Technologies
    • Non-linear Passives
    • Oscillators
    • Passive Sensors
    • Resistors
    • RF & Microwave
    • Telecommunication

    Resonant MLCC OBC Application Guide

    Bourns Releases New Compact Size High Current Ferrite Beads

    Skeleton Demonstrated Supercapacitor Based Shuttle Charging in Seconds

    NICHICON SLB Small Lithium-Titanate Rechargeable Batteries

    Skeleton Unveils the Leipzig Supercapacitor Factory

    Snubber Capacitors in Power Electronics

    TAIYO YUDEN Expands Lineup of Multilayer Metal Power Inductors

    Bourns Releases New High Energy Gas Discharge Tubes

    Würth Elektronik Extends its Application and Industry Guide for Easy Navigation to Suitable Circuits and Components

    Trending Tags

    • Ripple Current
    • RF
    • Leakage Current
    • Tantalum vs Ceramic
    • Snubber
    • Low ESR
    • Feedthrough
    • Derating
    • Dielectric Constant
    • New Products
    • Market Reports
  • VideoFilter
    • All
    • Antenna videos
    • Capacitor videos
    • Filter videos
    • Fuse videos
    • Inductor videos
    • Non-linear passives videos
    • Oscillator videos
    • Passive sensors videos
    • Resistor videos
    • Sensors

    Charging/Discharging of Linear andNon-linear Capacitors

    How to Select Inductor For Switching Power Supply

    Oscillators Integration, Selection Guide and Design In

    Input Capacitor Selection for Power Supplies – Part 3: Electrolytic Capacitors

    Input Capacitor Selection for Power Supplies Part 2 – Ceramic Capacitors

    Input Capacitor Selection for Power Supplies Video (Part 1)

    Vishay Webinar: Components Selection for Solar Panel Systems

    Capacitors Basics: Decoupling

    Totem Pole PFC Design for E-Mobility; Microchip and WE Video

    Trending Tags

    • Capacitors explained
    • Inductors explained
    • Resistors explained
    • Filters explained
    • Application Video Guidelines
    • EMC
    • New Products
    • Ripple Current
    • Simulation
    • Tantalum vs Ceramic
  • Knowledge Blog
  • Suppliers
    • Preferred Suppliers
    • Who is Who
  • Events
  • Home
  • NewsFilter
    • All
    • Aerospace & Defence
    • Antenna
    • Applications
    • Automotive
    • Capacitors
    • Circuit Protection Devices
    • Filters
    • Fuses
    • Inductors
    • Industrial
    • Integrated Passives
    • Market & Supply Chain
    • Medical
    • New Materials & Supply
    • New Technologies
    • Non-linear Passives
    • Oscillators
    • Passive Sensors
    • Resistors
    • RF & Microwave
    • Telecommunication

    Resonant MLCC OBC Application Guide

    Bourns Releases New Compact Size High Current Ferrite Beads

    Skeleton Demonstrated Supercapacitor Based Shuttle Charging in Seconds

    NICHICON SLB Small Lithium-Titanate Rechargeable Batteries

    Skeleton Unveils the Leipzig Supercapacitor Factory

    Snubber Capacitors in Power Electronics

    TAIYO YUDEN Expands Lineup of Multilayer Metal Power Inductors

    Bourns Releases New High Energy Gas Discharge Tubes

    Würth Elektronik Extends its Application and Industry Guide for Easy Navigation to Suitable Circuits and Components

    Trending Tags

    • Ripple Current
    • RF
    • Leakage Current
    • Tantalum vs Ceramic
    • Snubber
    • Low ESR
    • Feedthrough
    • Derating
    • Dielectric Constant
    • New Products
    • Market Reports
  • VideoFilter
    • All
    • Antenna videos
    • Capacitor videos
    • Filter videos
    • Fuse videos
    • Inductor videos
    • Non-linear passives videos
    • Oscillator videos
    • Passive sensors videos
    • Resistor videos
    • Sensors

    Charging/Discharging of Linear andNon-linear Capacitors

    How to Select Inductor For Switching Power Supply

    Oscillators Integration, Selection Guide and Design In

    Input Capacitor Selection for Power Supplies – Part 3: Electrolytic Capacitors

    Input Capacitor Selection for Power Supplies Part 2 – Ceramic Capacitors

    Input Capacitor Selection for Power Supplies Video (Part 1)

    Vishay Webinar: Components Selection for Solar Panel Systems

    Capacitors Basics: Decoupling

    Totem Pole PFC Design for E-Mobility; Microchip and WE Video

    Trending Tags

    • Capacitors explained
    • Inductors explained
    • Resistors explained
    • Filters explained
    • Application Video Guidelines
    • EMC
    • New Products
    • Ripple Current
    • Simulation
    • Tantalum vs Ceramic
  • Knowledge Blog
  • Suppliers
    • Preferred Suppliers
    • Who is Who
  • Events
No Result
View All Result
Passive Components Blog
No Result
View All Result

Memristors power quick-learning neural network

26.12.2017
Reading Time: 3 mins read
A A
9
VIEWS

source: Phys org news

A new type of neural network made with memristors can dramatically improve the efficiency of teaching machines to think like humans.

RelatedPosts

Resonant MLCC OBC Application Guide

Bourns Releases New Compact Size High Current Ferrite Beads

Skeleton Demonstrated Supercapacitor Based Shuttle Charging in Seconds

The network, called a reservoir computing system, could predict words before they are said during conversation, and help predict future outcomes based on the present.

The research team that created the reservoir computing system, led by Wei Lu, professor of electrical engineering and computer science at the University of Michigan, recently published their work in Nature Communications.

Reservoir computing systems, which improve on a typical neural network’s capacity and reduce the required training time, have been created in the past with larger optical components. However, the U-M group created their system using memristors, which require less space and can be integrated more easily into existing silicon-based electronics.

Memristors are a special type of resistive device that can both perform logic and store data. This contrasts with typical computer systems, where processors perform logic separate from memory modules. In this study, Lu’s team used a special memristor that memorizes events only in the near history.

Inspired by brains, neural networks are composed of neurons, or nodes, and synapses, the connections between nodes.

To train a neural network for a task, a neural network takes in a large set of questions and the answers to those questions. In this process of what’s called supervised learning, the connections between nodes are weighted more heavily or lightly to minimize the amount of error in achieving the correct answer.

Once trained, a neural network can then be tested without knowing the answer. For example, a system can process a new photo and correctly identify a human face, because it has learned the features of human faces from other photos in its training set.

“A lot of times, it takes days or months to train a network,” Lu said. “It is very expensive.”

Image recognition is also a relatively simple problem, as it doesn’t require any information apart from a static image. More complex tasks, such as speech recognition, can depend highly on context and require neural networks to have knowledge of what has just occurred, or what has just been said.

 “When transcribing speech to text or translating languages, a word’s meaning and even pronunciation will differ depending on the previous syllables,” Lu said.

This requires a recurrent neural network, which incorporates loops within the network that give the network a memory effect. However, training these recurrent neural networks is especially expensive, Lu said.

Reservoir computing systems built with memristors, however, can skip most of the expensive training process and still provide the network the capability to remember. This is because the most critical component of the system—the reservoir—does not require training.

When a set of data is inputted into the reservoir, the reservoir identifies important time-related features of the data, and hands it off in a simpler format to a second network. This second network then only needs training like simpler neural networks, changing weights of the features and outputs that the first network passed on until it achieves an acceptable level of error.

“The beauty of reservoir computing is that while we design it, we don’t have to train it,” Lu said.

The team proved the reservoir computing concept using a test of handwriting recognition, a common benchmark among neural networks. Numerals were broken up into rows of pixels, and fed into the computer with voltages like Morse code, with zero volts for a dark pixel and a little over one volt for a white pixel.

Using only 88 memristors as nodes to identify handwritten versions of numerals, compared to a conventional network that would require thousands of nodes for the task, the reservoir achieved 91 percent accuracy.

Reservoir computing systems are especially adept at handling data that varies with time, like a stream of data or words, or a function depending on past results.

To demonstrate this, the team tested a complex function that depended on multiple past results, which is common in engineering fields. The reservoir computing system was able to model the complex function with minimal error.

Lu plans on exploring two future paths with this research: speech recognition and predictive analysis.

“We can make predictions on natural spoken language, so you don’t even have to say the full word,” Lu said. “We could actually predict what you plan to say next.”

In predictive analysis, Lu hopes to use the system to take in signals with noise, like static from far-off radio stations, and produce a cleaner stream of data.

“It could also predict and generate an output signal even if the input stopped,” he said.

 

 

featured image:

A nanocomponent that is capable of learning: The Bielefeld memristor built into a chip is 600 times thinner than a human hair. Credit: Bielefeld University

 

Related Posts

Inductors

Bourns Releases New Compact Size High Current Ferrite Beads

2.10.2023
2
Industrial

NICHICON SLB Small Lithium-Titanate Rechargeable Batteries

2.10.2023
5
Capacitors

Würth Elektronik Extends its Application and Industry Guide for Easy Navigation to Suitable Circuits and Components

26.9.2023
41

Upcoming Events

Oct 3
October 3 @ 12:00 - October 5 @ 14:00 EDT

Design and Test of Non-Hermetic Microelectronic

Oct 11
11:00 - 12:00 CEST

Stretchable Electronics

Oct 16
October 16 - October 19

Digital WE Days 2023 – Virtual Conference

View Calendar

Popular Posts

  • What is a Dielectric Constant of Plastic Materials ?

    4 shares
    Share 4 Tweet 0
  • Ripple Current and its Effects on the Performance of Capacitors

    3 shares
    Share 3 Tweet 0
  • Understanding High-Precision Resistor Temperature Coefficient of Resistance

    0 shares
    Share 0 Tweet 0
  • Why Low ESR Matters in Capacitor Design

    0 shares
    Share 0 Tweet 0
  • Leakage Current Characteristics of Capacitors

    0 shares
    Share 0 Tweet 0
  • Capacitor Selection for Coupling and Decoupling Applications

    28 shares
    Share 28 Tweet 0
  • Coefficient of Linear Thermal Expansion on Polymers Explained

    0 shares
    Share 0 Tweet 0
  • How to Choose the Right Inductor for DC-DC Buck Applications

    0 shares
    Share 0 Tweet 0

Newsletter Subscription

 

Archive

2023
2022
2021
2020
2019
2018
2017

Symposium

Passive Components Networking Symposium

Passives e-Learning

Knowledge Blog

  • Home
  • Privacy Policy
  • EPCI Membership & Advertisement
  • About

© EPCI - Premium Passive Components Educational and Information Site

No Result
View All Result
  • Home
  • News
  • Video
  • Knowledge Blog
  • Preferred Suppliers
  • Events

© EPCI - Premium Passive Components Educational and Information Site

This website uses cookies. By continuing to use this website you are giving consent to cookies being used. Visit our Privacy and Cookie Policy.