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

Dense Connective Tissue01:13

Dense Connective Tissue

12.0K
Dense connective tissue contains more collagen fibers than loose connective tissue. As a consequence, it displays greater resistance to stretching. There are two major categories of dense connective tissue— regular and irregular.
Dense Regular Connective Tissue
In dense regular connective tissue, fibers are arranged parallel to each other, enhancing its tensile strength and resistance to stretching in the direction of the fiber orientations. Ligaments and tendons are made of dense regular...
12.0K
Association Areas of the Cortex01:21

Association Areas of the Cortex

9.4K
Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
9.4K
Associative Learning01:27

Associative Learning

1.3K
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
1.3K
System of Memory01:23

System of Memory

7.4K
Memory is categorized into three major systems: sensory memory, short-term memory (STM), and long-term memory (LTM). These systems differ in their capacity and the duration for which they can hold information. Sensory memory captures raw sensory input from the environment, holding it for just a few seconds or less. For example, on hearing a brief, loud sound, like a car horn honking, the sound seems to linger in the mind for a moment even after it stops. This is an instance of sensory memory...
7.4K
Working Memory01:24

Working Memory

883
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...
883
Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

423
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
423

You might also read

Related Articles

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

Sort by
Same author

Building transformers from neurons and astrocytes.

Proceedings of the National Academy of Sciences of the United States of America·2023
Same author

Modern Hopfield Networks for graph embedding.

Frontiers in big data·2022
Same author

Unsupervised learning by competing hidden units.

Proceedings of the National Academy of Sciences of the United States of America·2019
Same author

Morphogenesis at criticality.

Proceedings of the National Academy of Sciences of the United States of America·2014
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

Related Experiment Video

Updated: Feb 4, 2026

C. elegans Positive Butanone Learning, Short-term, and Long-term Associative Memory Assays
09:58

C. elegans Positive Butanone Learning, Short-term, and Long-term Associative Memory Assays

Published on: March 11, 2011

30.5K

Dense Associative Memory Is Robust to Adversarial Inputs.

Dmitry Krotov1, John Hopfield2

  • 1Institute for Advanced Study, Princeton, NJ 08540, U.S.A. krotov@ias.edu.

Neural Computation
|October 14, 2018
PubMed
Summary
This summary is machine-generated.

Dense associative memory (DAM) models with higher-order interactions offer improved robustness against adversarial and rubbish inputs compared to deep neural networks (DNNs). These models ensure learned patterns are semantically meaningful and can detect malicious attacks.

More Related Videos

The Double-H Maze: A Robust Behavioral Test for Learning and Memory in Rodents
09:01

The Double-H Maze: A Robust Behavioral Test for Learning and Memory in Rodents

Published on: July 8, 2015

13.1K
Shuttle Box Assay as an Associative Learning Tool for Cognitive Assessment in Learning and Memory Studies using Adult Zebrafish
08:35

Shuttle Box Assay as an Associative Learning Tool for Cognitive Assessment in Learning and Memory Studies using Adult Zebrafish

Published on: July 12, 2021

5.0K

Related Experiment Videos

Last Updated: Feb 4, 2026

C. elegans Positive Butanone Learning, Short-term, and Long-term Associative Memory Assays
09:58

C. elegans Positive Butanone Learning, Short-term, and Long-term Associative Memory Assays

Published on: March 11, 2011

30.5K
The Double-H Maze: A Robust Behavioral Test for Learning and Memory in Rodents
09:01

The Double-H Maze: A Robust Behavioral Test for Learning and Memory in Rodents

Published on: July 8, 2015

13.1K
Shuttle Box Assay as an Associative Learning Tool for Cognitive Assessment in Learning and Memory Studies using Adult Zebrafish
08:35

Shuttle Box Assay as an Associative Learning Tool for Cognitive Assessment in Learning and Memory Studies using Adult Zebrafish

Published on: July 12, 2021

5.0K

Area of Science:

  • Computational neuroscience
  • Machine learning
  • Artificial intelligence

Background:

  • Supervised deep neural networks (DNNs) exhibit vulnerabilities, including learning "rubbish" or "fooling" images lacking semantic similarity and susceptibility to adversarial perturbations that cause misclassification.
  • These issues highlight discrepancies between DNN and human pattern recognition, prompting research into learning algorithms that better emulate human perception.

Purpose of the Study:

  • To investigate dense associative memory (DAM) models with higher-order energy functions as a potential solution to DNN vulnerabilities.
  • To determine if DAM models can overcome issues of semantically meaningless minima and adversarial attacks, thereby mimicking human perception more accurately.

Main Methods:

  • Analysis of dense associative memory (DAM) models defined by energy functions with higher-order (greater than quadratic) interactions between neurons.
  • Examination of model properties in the limit of sufficiently large interaction vertex power.
  • Comparison of DAM models with higher-order interactions against DNNs with rectified linear units, particularly concerning adversarial image transferability.

Main Results:

  • DAM models with sufficiently high-order interactions exhibit minima free from rubbish images, ensuring semantically meaningful learned patterns.
  • Artificial patterns at decision boundaries in these models appear ambiguous to humans, reflecting aspects of both adjacent classes.
  • Adversarial images generated by lower-order models (equivalent to DNNs) fail to fool higher-order DAM models, indicating robustness.

Conclusions:

  • Dense associative memory models with higher-order energy functions demonstrate superior robustness against adversarial and rubbish inputs compared to standard DNNs.
  • These higher-order models offer a promising direction for developing more human-like perception and for detecting and mitigating adversarial attacks in AI systems.