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

Convolution Properties II01:17

Convolution Properties II

278
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...
278
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

391
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...
391
Association Areas of the Cortex01:21

Association Areas of the Cortex

6.2K
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,...
6.2K
Convolution Properties I01:20

Convolution Properties I

232
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:
232
Deconvolution01:20

Deconvolution

246
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
246
Neural Circuits01:25

Neural Circuits

1.5K
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...
1.5K

You might also read

Related Articles

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

Sort by
Same author

Two-year outcome of high-risk benign prostate hyperplasia patients treated with transurethral prostate resection by plasmakinetic or conventional procedure.

Urology·2012
Same author

Combination therapy improves exercise capacity and reduces risk of clinical worsening in patients with pulmonary arterial hypertension: a meta-analysis.

Journal of cardiovascular pharmacology·2012
Same author

Tailored design of architecturally controlled Pt nanoparticles with huge surface areas toward superior unsupported Pt electrocatalysts.

ACS applied materials & interfaces·2012
Same author

Primary non-Hodgkin's lymphoma of the skull base: a case report and literature review.

Clinical neurology and neurosurgery·2012
Same author

Mitigation of augmented extrasynaptic NMDAR signaling and apoptosis in cortico-striatal co-cultures from Huntington's disease mice.

Neurobiology of disease·2012
Same author

Strong inhibition of celastrol towards UDP-glucuronosyl transferase (UGT) 1A6 and 2B7 indicating potential risk of UGT-based herb-drug interaction.

Molecules (Basel, Switzerland)·2012

Related Experiment Video

Updated: Sep 7, 2025

Topographical Estimation of Visual Population Receptive Fields by fMRI
06:02

Topographical Estimation of Visual Population Receptive Fields by fMRI

Published on: February 3, 2015

9.3K

RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks.

Shanghua Gao, Zhong-Yu Li, Qi Han

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |June 17, 2022
    PubMed
    Summary

    This study introduces a search scheme to discover optimal receptive field combinations for AI models, improving performance on diverse tasks like action segmentation and object detection.

    More Related Videos

    Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings
    07:08

    Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings

    Published on: August 1, 2018

    8.4K
    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
    12:27

    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

    Published on: February 15, 2017

    7.0K

    Related Experiment Videos

    Last Updated: Sep 7, 2025

    Topographical Estimation of Visual Population Receptive Fields by fMRI
    06:02

    Topographical Estimation of Visual Population Receptive Fields by fMRI

    Published on: February 3, 2015

    9.3K
    Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings
    07:08

    Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings

    Published on: August 1, 2018

    8.4K
    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
    12:27

    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

    Published on: February 15, 2017

    7.0K

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Artificial Intelligence

    Background:

    • Receptive fields in AI models are crucial for processing sequential and spatial data, with large fields capturing long-range dependencies and small fields focusing on local details.
    • Current approaches rely on manually designing receptive field configurations within model layers, limiting adaptability and optimal performance.
    • The need exists for automated methods to discover effective receptive field combinations beyond human-designed patterns.

    Purpose of the Study:

    • To investigate the feasibility of automatically searching for optimal receptive field combinations in deep learning models.
    • To develop a novel search scheme that can identify superior receptive field configurations compared to hand-designed ones.
    • To enhance the performance of various AI tasks by integrating an automated receptive field search mechanism.

    Main Methods:

    • A global-to-local search scheme was proposed, initiating with a broad search for coarse receptive field combinations.
    • An expectation-guided iterative local search was employed to refine these coarse combinations for optimal performance.
    • The developed receptive field search was integrated into existing model architectures, termed RF-Next.

    Main Results:

    • The RF-Next models demonstrated significant performance improvements across multiple challenging tasks, including temporal action segmentation, object detection, and instance segmentation.
    • The automated search successfully identified receptive field combinations that outperformed traditional, hand-designed patterns.
    • The approach proved effective in diverse applications, including speech synthesis, highlighting its versatility.

    Conclusions:

    • Automated search for receptive field combinations offers a powerful alternative to manual design, leading to enhanced model performance.
    • The proposed global-to-local search scheme effectively identifies and refines receptive field configurations for diverse AI tasks.
    • The RF-Next framework provides a flexible and effective method for improving various computer vision and sequential data processing applications.