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

Working Memory01:24

Working Memory

482
Working memory refers to a combination of components, including short-term memory and attention, that allow an individual to hold information temporarily as we perform cognitive tasks. It is an essential cognitive function that enables the execution of complex tasks such as problem-solving, comprehension, and reasoning. Unlike short-term memory, which simply involves the storage of information for a brief period, working memory involves the active manipulation and processing of this...
482
Long-Term Memory01:18

Long-Term Memory

329
Long-term memory is a relatively permanent type of memory, capable of storing vast amounts of information over extended periods. Its storage capacity is generally considered unlimited.
Long-term memory can be categorized into two primary types: explicit and implicit memory. Explicit memory, also known as declarative memory, involves the conscious recollection of information that we deliberately try to remember, recall, and articulate. This type of memory encompasses specific facts, events, and...
329
Storage01:23

Storage

159
A schema is a mental framework that helps individuals organize and interpret information. Schemata, formed from previous experiences, influence how we process new information: how we encode it, the inferences we make, and how we retrieve it. For instance, a schema for what a typical classroom looks like might include desks, a teacher's desk, a whiteboard, and students in such an environment. This expectation helps us quickly understand and navigate new classrooms without needing to analyze...
159
Elaborative Rehearsals01:07

Elaborative Rehearsals

148
Elaborative rehearsal is a crucial cognitive strategy that strengthens information encoding in long-term memory by making meaningful connections between new data and pre-existing knowledge. This approach contrasts with maintenance rehearsal, which involves simple repetition without delving into the significance of the information. While maintenance rehearsal might temporarily keep information active in short-term memory, it is less effective for long-term retention.
The effectiveness of...
148
Understanding Memory01:19

Understanding Memory

703
Memory is the retention of information or experiences over time, facilitated through three main processes: encoding, storage, and retrieval. Encoding is the process of inputting information into the memory system. For instance, when listening to a lecture, watching a play, reading a book, or having a conversation, the brain is actively encoding information. This initial stage involves transforming sensory input into a form that can be processed and stored by the brain. Various factors, such as...
703
Higher Mental Functions of Brain: Learning and Memory01:26

Higher Mental Functions of Brain: Learning and Memory

1.3K
Memory is one of the most vital higher mental functions of the brain. Memory is closely related to learning because it enables us to retain information and experiences from our past to use them in our present life. It also helps us to remember facts, events, and skills, such as riding a bike or swimming. There are two types of memory — declarative memory, which involves memorizing facts or events, and procedural memory, which enables us to remember how to do something like writing or...
1.3K

You might also read

Related Articles

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

Sort by
Same author

A Unified Masked Jigsaw Puzzle Framework for Vision and Language Models.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

The aporetic dialogs of Modena on gender differences: Is it all about testosterone? Episode III: Mathematics.

Andrology·2025
Same author

VATr++: Choose Your Words Wisely for Handwritten Text Generation.

IEEE transactions on pattern analysis and machine intelligence·2024
Same author

Computer Vision in Human Analysis: From Face and Body to Clothes.

Sensors (Basel, Switzerland)·2023
Same author

Predicting gene and protein expression levels from DNA and protein sequences with Perceiver.

Computer methods and programs in biomedicine·2023
Same author

Fashion-Oriented Image Captioning with External Knowledge Retrieval and Fully Attentive Gates.

Sensors (Basel, Switzerland)·2023
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Related Experiment Video

Updated: Oct 19, 2025

Working Memory Training for Older Participants: A Control Group Training Regimen and Initial Intellectual Functioning Assessment
07:01

Working Memory Training for Older Participants: A Control Group Training Regimen and Initial Intellectual Functioning Assessment

Published on: September 20, 2020

4.9K

Working Memory Connections for LSTM.

Federico Landi1, Lorenzo Baraldi1, Marcella Cornia1

  • 1Department of Engineering "Enzo Ferrari", University of Modena and Reggio Emilia, Modena, Italy.

Neural Networks : the Official Journal of the International Neural Network Society
|September 21, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces Working Memory Connections to improve Long Short-Term Memory (LSTM) networks. By allowing internal cell states to influence gates, LSTMs achieve better performance on sequence modeling tasks.

Keywords:
Cell-to-gate connectionsGated RNNsImage captioningLanguage modelingLong Short-Term Memory networks

More Related Videos

An Appetitive Spatial Working Memory Task for Mice in a Semi-Automated 8-Arm Radial Maze, Reducing Fearful Memory Association in the Maze
14:24

An Appetitive Spatial Working Memory Task for Mice in a Semi-Automated 8-Arm Radial Maze, Reducing Fearful Memory Association in the Maze

Published on: July 29, 2025

904
Transcranial Direct Current Stimulation tDCS for Memory Enhancement
10:37

Transcranial Direct Current Stimulation tDCS for Memory Enhancement

Published on: September 18, 2021

14.7K

Related Experiment Videos

Last Updated: Oct 19, 2025

Working Memory Training for Older Participants: A Control Group Training Regimen and Initial Intellectual Functioning Assessment
07:01

Working Memory Training for Older Participants: A Control Group Training Regimen and Initial Intellectual Functioning Assessment

Published on: September 20, 2020

4.9K
An Appetitive Spatial Working Memory Task for Mice in a Semi-Automated 8-Arm Radial Maze, Reducing Fearful Memory Association in the Maze
14:24

An Appetitive Spatial Working Memory Task for Mice in a Semi-Automated 8-Arm Radial Maze, Reducing Fearful Memory Association in the Maze

Published on: July 29, 2025

904
Transcranial Direct Current Stimulation tDCS for Memory Enhancement
10:37

Transcranial Direct Current Stimulation tDCS for Memory Enhancement

Published on: September 18, 2021

14.7K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Deep Learning

Background:

  • Recurrent Neural Networks (RNNs), particularly Long Short-Term Memory (LSTM) networks, are standard for sequence modeling due to their gating mechanisms mitigating gradient issues.
  • However, LSTMs do not directly utilize their internal memory cell's information within the gating process.

Purpose of the Study:

  • To enhance LSTM performance by enabling direct influence of the internal cell state on the gating mechanism.
  • To address limitations in previous attempts to integrate cell state information into LSTM gates.

Main Methods:

  • Introduced a novel modification called Working Memory Connection.
  • This involves adding a learnable nonlinear projection of the cell content directly into the LSTM gates.
  • The modification is designed to be task-agnostic and integrate seamlessly with classical LSTM architectures.

Main Results:

  • Extensive experiments demonstrate consistent performance improvements of LSTMs with Working Memory Connections across various tasks.
  • Identified and resolved a key issue that hindered the effectiveness of prior cell state integration methods.
  • The proposed modification proves particularly effective for handling longer sequences.

Conclusions:

  • The internal cell state of LSTMs contains valuable information that can significantly boost network performance when incorporated into the gate structure.
  • Working Memory Connections offer a robust and effective method for leveraging this information, outperforming vanilla LSTMs.