Jove
Visualize
Contact Us

Related Concept Videos

Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

495
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
495
Introduction to Learning01:18

Introduction to Learning

601
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
601
Convolution Properties II01:17

Convolution Properties II

323
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
323
Convolution Properties I01:20

Convolution Properties I

280
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
280
Observational Learning01:12

Observational Learning

383
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
383
Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

201
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...
201

You might also read

Related Articles

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

Sort by
Same author

Nested Grover's Algorithm for Tree Search.

Entropy (Basel, Switzerland)·2026
Same author

Multilevel Data Representation for Training Deep Helmholtz Machines.

Neural computation·2025
Same author

Quantum Machine Learning-Quo Vadis?

Entropy (Basel, Switzerland)·2024
Same author

Can a Hebbian-like learning rule be avoiding the curse of dimensionality in sparse distributed data?

Biological cybernetics·2024
Same author

Promoting the Shift From Pixel-Level Correlations to Object Semantics Learning by Rethinking Computer Vision Benchmark Data Sets.

Neural computation·2024
Same author

Competitive learning to generate sparse representations for associative memory.

Neural networks : the official journal of the International Neural Network Society·2023
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
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 Experiment Video

Updated: Oct 15, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

685

Simple Convolutional-Based Models: Are They Learning the Task or the Data?

Luis Sa-Couto1, Andreas Wichert2

  • 1Department of Computer Science and Engineering, INESC-ID and Instituto Superior, Técnico University of Lisbon, 2744-016 Porto Salvo, Portugal luis.sa.couto@tecnico.ulisboa.pt.

Neural Computation
|October 28, 2021
PubMed
Summary
This summary is machine-generated.

Convolutional neural networks (CNNs) show high accuracy on training data but overfit. Unsupervised models with built-in invariance generalize better to new datasets, despite lower performance on familiar data.

Related Experiment Videos

Last Updated: Oct 15, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

685

Area of Science:

  • Computer Vision
  • Machine Learning
  • Computational Neuroscience

Background:

  • Convolutional Neural Networks (CNNs) are inspired by the visual cortex and utilize supervised learning.
  • Typical CNNs prioritize end-to-end training and backpropagation, leading to high accuracy but potential overfitting.
  • Alternative neocognitron models incorporate unsupervised learning and built-in invariance mechanisms.

Purpose of the Study:

  • To investigate the generalization capabilities of supervised CNNs versus unsupervised neocognitron models.
  • To test the hypothesis that supervised CNNs overfit, while unsupervised models with invariance generalize better.
  • To compare model performance on the same task across different datasets.

Main Methods:

  • Handwritten digit classification task using MNIST and ETL-1 datasets.
  • Comparison of a standard supervised CNN with a neocognitron-based model (What-Where).
  • Experimentation with various preprocessing techniques to standardize datasets.

Main Results:

  • Supervised CNNs outperformed the neocognitron model on the same dataset.
  • Both models exhibited overfitting when tested on a different dataset without retraining.
  • The unsupervised neocognitron model demonstrated superior generalization to the unseen dataset.

Conclusions:

  • Supervised learning in CNNs leads to overfitting and poor generalization to new data.
  • Unsupervised learning and built-in invariance mechanisms enhance model generalization.
  • Model architecture and learning paradigms significantly impact performance across diverse datasets.