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

Fast Fourier Transform01:10

Fast Fourier Transform

456
The Fast Fourier Transform (FFT) is a computational algorithm designed to compute the Discrete Fourier Transform (DFT) efficiently. By breaking down the calculations into smaller, manageable sections, the FFT significantly reduces the computational complexity involved. Direct computation of an N-point DFT requires N2 complex multiplications, whereas the FFT algorithm needs only (N/2)log⁡2N multiplications, offering a much faster performance.
The computational efficiency of the FFT becomes...
456
Parallel Processing01:20

Parallel Processing

220
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
220
Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

130
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
130
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

386
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...
386
Reconstruction of Signal using Interpolation01:10

Reconstruction of Signal using Interpolation

322
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
322
Bandpass Sampling01:17

Bandpass Sampling

254
In signal processing, bandpass sampling is an effective technique for sampling signals that have most of their energy concentrated within a narrow frequency band. This type of signal is known as a bandpass signal. The key principle of bandpass sampling involves sampling the signal at a rate that is greater than twice the signal's bandwidth to prevent aliasing.
A bandpass signal has a spectrum with a lower frequency limit, denoted as ω1, and an upper frequency limit, denoted as ω2....
254

You might also read

Related Articles

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

Sort by
Same author

DSSCC net enhanced skin cancer classification using SMOTE Tomek and optimized convolutional neural network.

Scientific reports·2025
Same author

Semantic web ontology for structured knowledge representation and clinical decision support in eye diseases.

Scientific reports·2025
Same author

Semantic web-based ontology: a comprehensive framework for cardiovascular knowledge representation.

BMC cardiovascular disorders·2025
Same author

Outdoor RGB and Point Cloud Depth Dataset for Palm Oil Fresh Fruit Bunch Ripeness Classification and Localization.

Scientific data·2025
Same author

Multi-View Human Action Recognition Using Skeleton Based-FineKNN with Extraneous Frame Scrapping Technique.

Sensors (Basel, Switzerland)·2023
Same author

Prediction of Oil Palm Yield Using Machine Learning in the Perspective of Fluctuating Weather and Soil Moisture Conditions: Evaluation of a Generic Workflow.

Plants (Basel, Switzerland)·2022

Related Experiment Video

Updated: Sep 7, 2025

Simultaneous Monitoring of Wireless Electrophysiology and Memory Behavioral Test as a Tool to Study Hippocampal Neurogenesis
07:25

Simultaneous Monitoring of Wireless Electrophysiology and Memory Behavioral Test as a Tool to Study Hippocampal Neurogenesis

Published on: August 20, 2020

3.8K

Computation and memory optimized spectral domain convolutional neural network for throughput and energy-efficient

Shahriyar Masud Rizvi1, Ab Al-Hadi Ab Rahman1, Usman Ullah Sheikh1

  • 1VeCAD Research Laboratory, School of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, 81310 Johor Malaysia.

Applied Intelligence (Dordrecht, Netherlands)
|June 22, 2022
PubMed
Summary
This summary is machine-generated.

Spectral domain Convolutional Neural Networks (SpCNNs) reduce computational costs for efficient AI inference. This study optimizes SpCNNs by reducing feature map size and depth, significantly boosting performance and energy efficiency with minimal accuracy loss.

Keywords:
Computational workloadConvolutional neural networkEnergy efficiencyMemory access costSpectral domain CNN

More Related Videos

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

654
Lensless Fluorescent Microscopy on a Chip
11:23

Lensless Fluorescent Microscopy on a Chip

Published on: August 17, 2011

17.8K

Related Experiment Videos

Last Updated: Sep 7, 2025

Simultaneous Monitoring of Wireless Electrophysiology and Memory Behavioral Test as a Tool to Study Hippocampal Neurogenesis
07:25

Simultaneous Monitoring of Wireless Electrophysiology and Memory Behavioral Test as a Tool to Study Hippocampal Neurogenesis

Published on: August 20, 2020

3.8K
Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

654
Lensless Fluorescent Microscopy on a Chip
11:23

Lensless Fluorescent Microscopy on a Chip

Published on: August 17, 2011

17.8K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Conventional Convolutional Neural Networks (CNNs) incur high computational workload and memory access costs (CMC).
  • Spectral domain CNNs (SpCNNs) present a computationally efficient alternative for CNN training and inference.
  • Optimizing CMC is crucial for enhancing CNN inference performance and energy efficiency.

Purpose of the Study:

  • To analytically investigate the CMC of SpCNNs and identify contributing factors.
  • To propose a methodology for optimizing CMC in SpCNNs to enhance inference performance.
  • To provide guidelines for designers to achieve a balance between performance, accuracy, and energy efficiency in SpCNNs.

Main Methods:

  • Analytical investigation of CMC in SpCNNs.
  • Development of a methodology to optimize CMC by reducing output feature map (OFM) size and/or depth.
  • Evaluation of the methodology on LeNet-5 and AlexNet architectures using MNIST and Fashion MNIST datasets.

Main Results:

  • LeNet-5 achieved up to 4.2x higher throughput and 10.5x greater energy efficiency with a maximum 3% accuracy loss.
  • AlexNet demonstrated up to 11.6x increased throughput and 25x more energy-efficient inference with a 4.4% accuracy reduction.
  • The proposed methodology offers significant performance and energy efficiency gains compared to state-of-the-art SpCNN models and baseline architectures.

Conclusions:

  • The proposed methodology effectively optimizes CMC in SpCNNs, leading to substantial improvements in inference performance and energy efficiency.
  • Reducing OFM size and depth, under accuracy constraints, is a viable strategy for performance-optimized CNN inference.
  • SpCNNs offer a promising direction for developing computationally efficient deep learning models for various applications.